{ "count" : 4781, "data" : [ { "id" : "6a305745f292fd229cf36f84", "title" : "Monteur Tracing", "industry" : "Tracing", "salary" : { "min" : 28000.0, "max" : 35000.0, "currency" : "EUR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for an entry-level Monteur Tracing in Rotterdam, Netherlands, adjusted for the manufacturing industry." }, "location" : "Rotterdam, Zuid-Holland, Nederland", "locations" : [ "Rotterdam, Zuid-Holland, Nederland" ], "certifications" : [ "Basic VCA certificate" ], "timestamp" : "2026-06-16T08:32:51.287", "fingerprint" : "8318427f88136af67df6689f0e2067b1c509df11155b52d3b5fc38887c495904", "source" : "recruitee", "language" : "nl", "applyUrl" : "https://bnlaltradservices.recruitee.com/o/monteur-tracing-9/c/new", "externalId" : "2640364", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Rotterdam", "state" : "Zuid-Holland", "country" : "Netherlands", "continent" : "eu", "source" : "llm", "workMode" : "onsite", "geo" : "51.9244424,4.4777500" } ], "locationText" : "Rotterdam, Zuid-Holland, Netherlands", "employmentType" : "FULL_TIME", "minimumEducation" : "high school", "experienceMinYears" : 3, "experienceMaxYears" : 5, "experienceLevel" : "mid", "coreResponsibilities" : "Perform tracing work, Install and mount tracing, Read work specifications, Follow instructions and specifications, Maintain contact with stakeholders, Maintain contact with colleagues, Maintain contact with customers, Comply with legal standards, Comply with safety regulations", "teamCollaboration" : "Work in teams", "domainKnowledge" : "Steam tracing; Electrical tracing", "domainList" : [ "steam-tracing", "electrical-tracing" ], "domainSpecificKnowledge" : [ "Steam tracing", "Electrical tracing" ], "continuousLearning" : "Training opportunities; Further education", "specialRequirements" : "Work at heights", "qualificationsBasic" : "VMBO or equivalent, Basic VCA certificate, Driver's license category, Dutch language proficiency, Basic English/German speaking", "qualificationsPreferred" : "Relevant work experience", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "Als Monteur Tracing voer je in teamverband verschillende montage werkzaamheden uit op locatie bij de klant. Aan de hand van werkspecificaties en instructies kies je de juiste techniek en materialen. Vervolgens plaats en monteer je de stoom- of elektrische tracing op leidingen en installaties. Hierdoor blijven de leidingen op de gewenste tempratuur. Wat ga je doen? Uitvoeren tracing werkzaamheden. Plaatsen en monteren van tracing op leidingen, valves en kleppen (indien nodig inclusief kabelbanen en toe- en afvoerstations). Lezen van werkspecificaties en instructies. Je zorgt ervoor dat taken worden uitgevoerd volgens de instructies en specificaties. Contact onderhouden met stakeholders. Contact onderhouden met collega’s en klanten over de voortgang van het werk Naleven van de wettelijke normen en veiligheidsvoorschriften. Het werk uitvoeren volgens wettelijke standaarden en vastgestelde veiligheidsvoorschriften. Wat bieden wij jou? * Een afwisselende en uitdagende functie binnen een dynamische organisatie * Leuke werksfeer met aandacht voor jou als mens * Spannend en afwisselend werk op grote hoogtes en diverse projecten * Een aantrekkelijk salaris en 8% vakantiegeld * 25 vakantiedagen en 13 ADV-dagen (o.b.v. 40 uur) * Geen vooropleiding nodig – volop kansen voor opleiding en bijscholing * Pensioen via PMT ## Requirements Wie ben jij?? * VMBO-opleiding of een vergelijkbaar denk- en werkniveau * Een basis VCA-certificaat, of bereidheid om deze te behalen * Enige relevante werkervaring is een pluspunt, maar geen vereiste * Een rijbewijs categorie B * Goede beheersing van de Nederlandse taal en basis spreekvaardigheid in Engels en/of Duits Wie zijn wij? Vakmanschap, samenwerking en persoonlijke groei staan bij ons centraal. Onze projecten zijn uitdagend en divers, van industriële isolatie tot indrukwekkende steigerconstructies. Geen dag is hetzelfde! Sluit je aan en bouw mee aan de toekomst – letterlijk én figuurlijk. Interesse? Solliciteer direct via de sollicitatiebutton! Heb je vragen over deze vacature? Bel of app Joost voor meer informatie op 0616167808. Together building a sustainable future!", "summaryDescription" : "Monteur Tracing. Perform tracing work. Install and mount tracing", "postedDate" : "2026-06-15T07:28:10.000", "createdAt" : "2026-06-15T22:40:02.693", "lastUpdated" : "2026-06-16T08:32:51.287", "ingestTimestamp" : "2026-06-15T22:40:02.693", "mongoId" : "6a305745f292fd229cf36f84", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "<30k", "hasSalary" : false, "allSkills" : [ "Steam tracing", "Electrical tracing", "Basic VCA certificate" ], "skillCount" : 3, "jobCategory" : "operations", "jobSubcategory" : "general", "seniorityLevel" : "Entry", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Manufacturing", "llmIndustryConfidence" : 0.92 }, { "id" : "6a305745f292fd229cf36f7f", "title" : "Uitvoerder Elektrische Tracing", "industry" : "Tracing", "salary" : { "min" : 70000.0, "max" : 95000.0, "currency" : "EUR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for Lead Uitvoerder Elektrische Tracing in Amsterdam, Netherlands, adjusted for the manufacturing industry." }, "location" : "Amsterdam, Noord-Holland, Nederland", "locations" : [ "Amsterdam, Noord-Holland, Nederland" ], "certifications" : [ "VCA-VOL" ], "timestamp" : "2026-06-16T07:23:18.289", "fingerprint" : "27e78d80fd21b539229d15348fe99cbae7c04882c824261642794ac46a7ef5a2", "source" : "recruitee", "language" : "nl", "applyUrl" : "https://bnlaltradservices.recruitee.com/o/uitvoerder-elektrische-tracing-1/c/new", "externalId" : "2640413", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Amsterdam", "state" : "Noord-Holland", "country" : "Netherlands", "continent" : "eu", "source" : "llm", "workMode" : "onsite", "geo" : "52.3730796,4.8924534" } ], "locationText" : "Amsterdam, Noord-Holland, Netherlands", "employmentType" : "FULL_TIME", "minimumEducation" : "vocational training", "experienceMinYears" : 3, "experienceMaxYears" : 5, "experienceLevel" : "mid", "professionalSkills" : [ "Leidinggeven", "Klantgerichtheid" ], "hardSkillsList" : [ "Elektrische tracing", "Materialenbeheer", "Kwaliteitscontrole", "Veiligheidsprocedures" ], "hardSkills" : [ { "name" : "Elektrische tracing", "level" : "intermediate" }, { "name" : "Materialenbeheer", "level" : "intermediate" }, { "name" : "Kwaliteitscontrole", "level" : "intermediate" }, { "name" : "Veiligheidsprocedures", "level" : "intermediate" } ], "majorSkills" : "Werkvoorbereiding, Team aansturing, Technische begeleiding", "majorSkillsList" : [ "Werkvoorbereiding", "Team aansturing", "Technische begeleiding" ], "coreResponsibilities" : "Bereiden werk op locatie, Zorgen efficiënte inzet mensen, Zorgen efficiënte inzet materiaal, Aansturen team, Begeleiden team, Ondersteunen projectleider, Organiseren werkzaamheden, Opstellen werkopdrachten, Opstellen instructies, Bestellen materialen, Beheren materialen, Bewaken voortgang, Signaleren afwijkingen planning, Signaleren afwijkingen uitvoering, Signaleren afwijkingen voorraad, Verdelen werk, Geven heldere instructies, Aansturen monteurs, Aansturen voormannen, Focus op veiligheid, Focus op kwaliteit, Focus op efficiëntie, Technische begeleiding elektrische tracing, Adviseren monteurs, Adviseren klanten, Opsporen afwijkingen, Opsporen storingen, Ondersteunen technische vraagstukken, Controleren kwaliteit werk, Doorvoeren correcties, Verzorgen meggertests, Rapporteren meggertests, Toezien op veilige werkomgeving, Zorgen correcte toepassing PBM's, Zorgen correcte toepassing gereedschappen, Zorgen correcte toepassing materialen, Onderhouden contact met klanten, Onderhouden contact met projectleiders, Onderhouden contact met collega's, Bespreken voortgang, Bespreken knelpunten, Bespreken meerwerk, Bespreken minderwerk, Verzorgen oplevering, Verzorgen as-built schetsen, Verzorgen revisietekeningen, Verzorgen projectadministratie", "teamCollaboration" : "Samenwerken met collega's; Samenwerken met stafdiensten", "projectManagementSkills" : [ "Werkvoorbereiding", "Planning", "Projectadministratie" ], "domainKnowledge" : "Elektrische tracing materialen", "domainList" : [ "elektrische-tracing-materialen" ], "domainSpecificKnowledge" : [ "Elektrische tracing materialen" ], "communicationSkills" : "Technische advisering; Rapportage", "documentationSkills" : "Werkopdrachten; Instructies; Projectadministratie; As-built schetsen; Revisietekeningen", "continuousLearning" : "Opleiding; Bijscholing", "problemSolvingSkills" : "Signaleren afwijkingen; Opsporen storingen", "specialRequirements" : "Rijbewijs", "outcomesObjectives" : "Veilig verloop projecten; Efficiënt verloop projecten; Klantgericht verloop projecten", "qualificationsBasic" : "MBO- werk- en denkniveau, Ervaring leidinggeven industriële dienstverlening, VCA-VOL, Vakgerichte cursussen, Beheersing Nederlandse taal, Spreekvaardigheid Engels, Spreekvaardigheid Duits, Rijbewijs", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "Als Uitvoerder Elektrische Tracing ben jij de schakel tussen de projectleider en de (meewerkend) voorman. Je bereidt het werk voor op locatie en zorgt voor een efficiënte inzet van mensen en materiaal. Met een coachende en motiverende leiderschapsstijl stuur je jouw team aan en werk je nauw samen met collega’s en stafdiensten. Daarnaast ondersteun je de projectleider met diverse taken. Wat ga je doen? Als Uitvoerder Elektrische Tracing ben jij de verbindende schakel tussen voorbereiding en uitvoering, waarbij je zorgt voor een veilig, efficiënt en klantgericht verloop van projecten. Voorbereiden en organiseren van werkzaamheden. Je stelt werkopdrachten en instructies op, bestelt en beheert materialen, bewaakt de voortgang en signaleert tijdig afwijkingen in planning, uitvoering of voorraad. Aansturen en begeleiden van het uitvoeringsteam. Je verdeelt het werk, geeft heldere instructies en stuurt monteurs en (meewerkend) voormannen aan, met focus op veiligheid, kwaliteit en efficiëntie. Technische begeleiding en advies elektrische tracing. Je beschikt over inhoudelijke kennis van diverse elektrische tracing materialen, adviseert monteurs en klanten, spoort afwijkingen en storingen op en ondersteunt bij technische vraagstukken. Kwaliteitscontrole en inspecties. Je controleert samen met het team de kwaliteit van het werk, voert correcties door waar nodig en verzorgt en rapporteert meggertests van geïnstalleerde electrical heat tracing systemen. Veiligheid, PBM’s en correct gebruik van middelen. Je ziet toe op een veilige werkomgeving en zorgt voor correcte toepassing van PBM’s, gereedschappen en materialen conform geldende voorschriften. Afstemming en oplevering. Je onderhoudt contact met klanten, projectleiders en collega’s over voortgang en knelpunten, meer- en minderwerk en verzorgt een correcte en volledige oplevering, inclusief as-built schets- en revisietekeningen en correcte en volledige projectadministratie. Wat kun je verwachten? * Een afwisselende en uitdagende functie binnen een dynamische organisatie * Leuke werksfeer met aandacht voor jou als mens * Mogelijkheden voor persoonlijke en professionele ontwikkeling, met volop kansen voor opleiding en bijscholing * Een aantrekkelijk salaris en 8% vakantiegeld * 25 vakantiedagen en 13 ADV dagen (o.b.v. 40 uur) * Pensioen via PMT ## Requirements Wat breng je mee? Jij bent proactief, klantgericht en een natuurlijke leider. Daarnaast heb je: * MBO- werk- en denkniveau * Ervaring op het gebied van leidinggeven binnen de industriële dienstverlening * VCA-VOL en vakgerichte cursussen * Beheersing Nederlandse taal en enige spreekvaardigheid in Engels en/of Duits * Een rijbewijs B Wie zijn wij? Vakmanschap, samenwerking en persoonlijke groei staan bij ons centraal. Onze projecten zijn uitdagend en divers, van industriële isolatie tot indrukwekkende steigerconstructies. Geen dag is hetzelfde! Sluit je aan en bouw mee aan de toekomst – letterlijk én figuurlijk. Interesse? Solliciteer direct via de sollicitatiebutton! Heb je vragen over deze vacature? Bel of app Joost voor meer informatie op 0616167808. Together building a sustainable future!", "summaryDescription" : "Uitvoerder Elektrische Tracing. Skills: Werkvoorbereiding, Team aansturing, Technische begeleiding. Bereiden werk op locatie. Zorgen efficiënte inzet mensen", "postedDate" : "2026-06-15T07:47:11.000", "createdAt" : "2026-06-15T22:39:49.451", "lastUpdated" : "2026-06-16T07:23:18.289", "ingestTimestamp" : "2026-06-15T22:39:49.451", "mongoId" : "6a305745f292fd229cf36f7f", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "50k-75k", "hasSalary" : false, "allSkills" : [ "Elektrische tracing", "Materialenbeheer", "Kwaliteitscontrole", "Veiligheidsprocedures", "Werkvoorbereiding", "Team aansturing", "Technische begeleiding", "Leidinggeven", "Klantgerichtheid", "Planning", "Projectadministratie", "Elektrische tracing materialen", "VCA-VOL" ], "skillCount" : 13, "jobCategory" : "operations", "jobSubcategory" : "general", "seniorityLevel" : "Lead", "dataQualityScore" : 0.8888889, "daysOld" : 0, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Manufacturing", "llmIndustryConfidence" : 0.92 }, { "id" : "693c2b8670f0b99d5843fab2", "title" : "Executive Assistant, AWS Monitoring and Observability", "company" : "Amazon Development Center U.S., Inc.", "industry" : "Administrative Support, Cloud Computing", "salary" : { "min" : 66800.0, "max" : 142800.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : false }, "location" : "Santa Clara, California, USA", "locations" : [ "Santa Clara, California, USA" ], "timestamp" : "2026-06-15T05:47:30.425", "fingerprint" : "c5f53b10c1585b696acb39aa89c7723651f1285509b5737d24b7effacf21a2f2", "source" : "amazon", "language" : "en", "applyUrl" : "https://account.amazon.com/jobs/3139837/apply", "externalId" : "cab7ac50-8029-4e77-8c22-f3cc261002ff", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Santa Clara", "state" : "California", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "37.2333253,-121.6846349" } ], "locationText" : "Santa Clara, California, United States", "employmentType" : "FULL_TIME", "coreResponsibilities" : "Coordinate and engage leadership in planning events, Organize events, activities and calendars, Orchestrate complex calendars, Schedule requirements, Prioritize executive's tasks and appointments, Ensure strategic alignment with business priorities, Serve as liaison between leadership and stakeholders, Facilitate clear communication channels, Manage sensitive information with discretion, Execute end-to-end travel logistics, Coordinate complex multi-city itineraries, Plan client-facing events, Plan team visits across corporate offices, Lead planning of events, Plan staff meetings, Plan all-hands meetings, Plan executive offsites, Plan team-building activities, Order supplies, Collaborate with EA Community across AWS, Drive best practices, Implement solutions, Drive organizational efficiency, Develop tracking systems for critical deliverables, Maintain tracking systems for critical deliverables, Ensure on-time completion of executive commitments, Ensure on-time completion of team commitments, Provide status updates to key stakeholders, Have fun at work, Help others have fun", "teamCollaboration" : "Executive leadership; Key stakeholders; Other Executive Assistants; EA Community across AWS; Security Services business; Observability business", "toolProficiency" : [ "Microsoft Office" ], "specialRequirements" : "Five days a week in office", "qualificationsBasic" : "Microsoft Office products and applications, 5+ years senior level leadership support, Managing executive level calendars, Domestic or international travel coordination", "qualificationsPreferred" : "Leading process improvements, Fast-paced, high-tech company experience, Designing processes to maximize efficiency", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "AWS Observability organization is seeking a proactive, customer service obsessed, and team-oriented Executive Assistant to support a VP leader in a key role within our org, based in our Seattle, WA offices. This role requires attention to detail, organizational skills, and the ability to meet tight deadlines and juggle multiple critical requests across internal and external stakeholders. You will act as a seamless extension of the supported VP and will work closely with other Executive Assistants throughout the organization as well as in the Security Services and Observability business. You will be comfortable in a fast-paced, goal-focused environment, while maintaining flexibility, a sense of humor and composure. Key to the position is the ability to be organized, understand business priorities, and to anticipate needs proactively while also serving as another \"go to\" for all members on this team. In addition, the ability to have a high level of integrity and discretion in handling confidential information and professionalism in dealing with senior professionals inside and outside the company is critical. You will possess the ability to complete complex tasks quickly with little guidance, react with appropriate urgency to situations that require a quick turnaround, and take effective action without having to know the whole picture. This role requires five (5) days a week in office. Key job responsibilities Responsibilities include but are not limited to: - Proactively coordinate and engage with leadership in planning and organizing events, activities and calendars - Orchestrate complex calendars, scheduling requirements, and prioritization of executive's tasks and appointments across time zones according to their importance, urgency, and relevance and ensuring strategic alignment with business priorities. - Serve as a trusted liaison between executive leadership and key stakeholders, facilitating clear communication channels and managing sensitive information with the highest level of discretion - Execute end-to-end travel logistics for international and domestic trips, including complex multi-city itineraries, client-facing events, and team visits across corporate offices. - Lead the planning of events including staff meetings, all-hands meetings, executive offsites, team-building activities, supply ordering. - Collaborate with the EA Community across AWS to drive best practices, implement solutions, and drive organizational efficiency. - Develop and maintain tracking systems for critical deliverables, ensuring on-time completion of executive and team commitments and providing regular status updates to key stakeholders. - Have fun at work and help others do the same! Basic Qualifications: - Experience with Microsoft Office products and applications - 5+ years of senior level leadership support experience - Experience managing executive level calendars - Experience with domestic or international travel coordination Preferred Qualifications: - Experience leading process improvements - Experience in a fast-paced, high-tech company - Experience designing processes to maximize efficiency Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status. Los Angeles County applicants: Job duties for this position include: work safely and cooperatively with other employees, supervisors, and staff; adhere to standards of excellence despite stressful conditions; communicate effectively and respectfully with employees, supervisors, and staff to ensure exceptional customer service; and follow all federal, state, and local laws and Company policies. Criminal history may have a direct, adverse, and negative relationship with some of the material job duties of this position. These include the duties and responsibilities listed above, as well as the abilities to adhere to company policies, exercise sound judgment, effectively manage stress and work safely and respectfully with others, exhibit trustworthiness and professionalism, and safeguard business operations and the Company’s reputation. Pursuant to the Los Angeles County Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records. Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner. Our compensation reflects the cost of labor across several US geographic markets. The base pay for this position ranges from $66,800/year in our lowest geographic market up to $142,800/year in our highest geographic market. Pay is based on a number of factors including market location and may vary depending on job-related knowledge, skills, and experience. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, please visit https://www.aboutamazon.com/workplace/employee-benefits . This position will remain posted until filled. Applicants should apply via our internal or external career site.", "summaryDescription" : "Executive Assistant, AWS Monitoring and Observability at Amazon Development Center U.S., Inc.. Coordinate and engage leadership in planning events. Organize events, activities and calendars", "postedDate" : "2026-06-13T13:39:59.573", "createdAt" : "2026-06-13T13:39:59.573", "lastUpdated" : "2026-06-15T05:47:30.425", "ingestTimestamp" : "2026-06-13T13:39:59.573", "mongoId" : "693c2b8670f0b99d5843fab2", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "sourceUrl" : "https://account.amazon.com/jobs/3139837/apply", "salaryAnnualMin" : 66800, "salaryAnnualMax" : 142800, "salaryBand" : "50k-75k", "hasSalary" : true, "allSkills" : [ "Microsoft Office" ], "skillCount" : 1, "jobCategory" : "operations", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true }, { "id" : "6a2c7f9a74d8ee00a0955d46", "title" : "Standards & Practices Content Analyst", "company" : "Crunchyroll, LLC", "salary" : { "min" : 485000.0, "max" : 725000.0, "currency" : "MXN", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for a Mid-level Standards & Practices Content Analyst in Mexico City, Mexico, with 2+ years of experience in the Media industry." }, "location" : "Mexico City, Mexico City, Mexico", "locations" : [ "Mexico City", "Mexico City", "Mexico" ], "timestamp" : "2026-06-16T02:42:14.620", "fingerprint" : "95a44c3da7f5aa93d11f56cc07f11de77b944a45df103abc65632d373df385ef", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://boards.greenhouse.io/crunchyroll/jobs/7990680?gh_jid=7990680", "externalId" : "7990680", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Mexico City", "state" : "Mexico City", "country" : "Mexico", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "19.4326296,-99.1331785" } ], "locationText" : "Mexico City, Mexico City, Mexico", "experienceMinYears" : 2, "rawDescription" : "About Crunchyroll Founded by fans, Crunchyroll delivers the art and culture of anime to a passionate community. We super-serve over 100 million anime and manga fans across 200+ countries and territories, and help them connect with the stories and characters they crave. Whether that experience is online or in-person, streaming video, theatrical, games, merchandise, events and more, it’s powered by the anime content we all love. Join our team, and help us shape the future of anime! The Standards & Practices team is responsible for ensuring that all content on the Crunchyroll platform adheres to our internal standards and complies with any legal/regulatory requirements in the countries where we operate. Our goal is to provide our audiences with content ratings and advisories to help them make informed viewing choices. The team embodies Crunchyroll’s collaborative spirit and operates at the intersection of compliance, content operations, and audience trust, playing a critical role in enabling scalable global content distribution while mitigating regulatory and brand risk. Responsibilities: Screen and take detailed content notes on new simulcast and library titles and digital manga Analyze content to determine the appropriate rating and content descriptors in multiple regions Maintain internal and external ratings databases Collaborate with other S&P team members to harmonize rating decisions Identify and escalate potential issues related to ratings and advisories to key stakeholders Perform series and marketplace research Assist department management with staying on top of shifting global attitudes around content. About You: 2+ years experience in broadcast/streaming/gaming standards and practices and/or content review Experience with content ratings systems and regulatory bodies Possess strong critical thinking and analytical skills Familiarity with global cultural, ethnic, geopolitical and religious sensitivities Proven ability to manage a high volume of projects with competing deadlines Excellent written communication skills, especially in conveying visual information clearly and concisely Familiarity with anime and manga highly preferred Ability to analyze and discuss sensitive, potentially offensive material dispassionately and clinically Comfortable with databases (eg Airtable) and structuring large amounts of metadata Excellent trouble-shooting and follow-up skills Ability to work independently Fluency in English required, proficiency in other languages (particularly Japanese and/or Spanish) a plus Ability to work flexible hours to accommodate international colleagues a plus This role requires screening and discussing content that may be sensitive or offensive to certain audiences. Why you will love working at Crunchyroll In addition to getting to work with fun, passionate and inspired colleagues, you will also enjoy the following benefits and perks: Receive a great compensation package including salary plus performance bonus earning potential, paid annually. Flexible time off policies allowing you to take the time you need to be your whole self. Generous medical, dental, vision, STD, LTD, and life insurance Health Saving Account HSA program Health care and dependent care FSA 401(k) plan, with employer match Employer paid commuter benefit Support program for new parents Pet insurance and some of our offices are pet friendly! #LifeAtCrunchyroll ((select from the following job modalities for this role: #LI-Hybrid #LI-remote #LI-onsite)) About our Values We want to be everything for someone rather than something for everyone and we do this by living and modeling our values in all that we do. We value Courage. We believe that when we overcome fear, we enable our best selves. Curiosity. We are curious, which is the gateway to empathy, inclusion, and understanding. Kaizen. We have a growth mindset committed to constant forward progress. Service. We serve our community with humility, enabling joy and belonging for others. Our commitment to diversity and inclusion Our mission of helping people belong reflects our commitment to diversity & inclusion. It's just the way we do business. We are an equal opportunity employer and value diversity at Crunchyroll. Pursuant to applicable law, we do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. Crunchyroll, LLC is an independently operated joint venture between US-based Sony Pictures Entertainment, and Japan's Aniplex, a subsidiary of Sony Music Entertainment (Japan) Inc., both subsidiaries of Tokyo-based Sony Group Corporation. Questions about Crunchyroll’s hiring process? Please check out our Hiring FAQs: https://help.crunchyroll.com/hc/en-us/articles/360040471712-Crunchyroll-Hiring-FAQs Please refer to our Candidate Privacy Policy for more information about how we process your personal information, and your data protection rights: https://tbcdn.talentbrew.com/company/22978/v1_0/docs/spe-jobs-privacy-policy-update-for-crpa-dec-21-22.pdf Please beware of recent scams to online job seekers. Those applying to our job openings will only be contacted directly from @crunchyroll.com email account.", "summaryDescription" : "Standards & Practices Content Analyst at Crunchyroll, LLC", "postedDate" : "2026-06-14T20:12:22.246", "createdAt" : "2026-06-14T20:12:22.246", "lastUpdated" : "2026-06-16T02:42:14.620", "ingestTimestamp" : "2026-06-14T20:12:22.246", "mongoId" : "6a2c7f9a74d8ee00a0955d46", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "operations", "jobSubcategory" : "general", "seniorityLevel" : "Mid", "dataQualityScore" : 0.6666667, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Media", "llmIndustryConfidence" : 0.95 }, { "id" : "6a305118f292fd229cef9890", "title" : "DevOps/Observability Engineer", "industry" : "IT", "salary" : { "min" : 85000.0, "max" : 130000.0, "currency" : "EUR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for Senior DevOps/Observability Engineer in Bulgaria, adjusted for remote work and the technology industry." }, "location" : "US", "locations" : [ "US" ], "timestamp" : "2026-06-16T11:07:52.421", "fingerprint" : "82d9f37dbd41a8f60e0c1b332cfacd5c74e0c06ed95d0f543573bafb4f863882", "source" : "lever", "language" : "en", "applyUrl" : "https://jobs.lever.co/jobgether/976aa58f-95cc-47d2-953f-822a5bcd5394/apply", "externalId" : "976aa58f-95cc-47d2-953f-822a5bcd5394", "industryFunction" : { }, "structuredLocations" : [ { "country" : "Bulgaria", "continent" : "eu", "workMode" : "remote" } ], "locationText" : "Bulgaria", "employmentType" : "FULL_TIME", "experienceMinYears" : 8, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "OpenTelemetry, Prometheus, Grafana, CloudWatch, CloudTrail, VPC Flow Logs, Splunk HEC, Alertmanager, PromQL, Terraform, Kubernetes, EKS, ECS", "professionalSkills" : [ "System design", "Cost optimization", "Performance optimization" ], "hardSkillsList" : [ "Observability architectures", "Log aggregation", "Alerting frameworks", "Infrastructure as Code", "Container orchestration" ], "hardSkills" : [ { "name" : "Observability architectures", "level" : "intermediate" }, { "name" : "Log aggregation", "level" : "intermediate" }, { "name" : "Alerting frameworks", "level" : "intermediate" }, { "name" : "Infrastructure as Code", "level" : "intermediate" }, { "name" : "Container orchestration", "level" : "intermediate" } ], "majorSkills" : "Observability, DevOps, AWS, Kubernetes", "majorSkillsList" : [ "Observability", "DevOps", "AWS", "Kubernetes" ], "coreResponsibilities" : "Design and implement end-to-end observability architectures, Build and maintain centralized observability pipelines, Develop scalable log aggregation and routing strategies, Create advanced alerting frameworks, Create high-quality dashboards, Deploy and manage observability infrastructure, Support Kubernetes and container-based observability, Optimize observability systems for performance, Optimize observability systems for cost efficiency, Optimize observability systems for scalability, Collaborate with engineering teams to improve system reliability, Collaborate with engineering teams to improve monitoring standards, Collaborate with engineering teams to improve incident response", "teamCollaboration" : "Engineering teams", "domainKnowledge" : "Cloud environments; Multi-account AWS; Distributed systems; Cloud-native environments", "domainList" : [ "cloud-environments", "multi-account-aws", "distributed-systems", "cloud-native-environments" ], "domainSpecificKnowledge" : [ "Cloud environments", "Multi-account AWS", "Distributed systems", "Cloud-native environments" ], "toolProficiency" : [ "OpenTelemetry", "Prometheus", "Grafana", "CloudWatch", "CloudTrail", "Splunk HEC", "Alertmanager", "Terraform", "Kubernetes" ], "continuousLearning" : "AI; Cloud; Platform engineering", "innovationCreativity" : "Innovation", "problemSolvingSkills" : "Problem-solving; Debugging", "qualificationsBasic" : "8+ years of experience in DevOps, Site Reliability Engineering, or Observability Engineering roles, Hands-on experience designing unified observability pipelines using OpenTelemetry, Prometheus, and Grafana, Deep expertise in AWS observability services including CloudWatch, CloudTrail, and cross-account telemetry strategies, Proven ability to build and manage large-scale log aggregation systems and optimize high-volume data pipelines, Experience with Kubernetes (EKS) or containerized environments (ECS) in production settings, Advanced proficiency with Terraform or other Infrastructure as Code tools for infrastructure and observability deployments, Experience building alerting systems, dashboards, and monitoring frameworks for distributed systems, Understanding of cost optimization strategies for observability platforms (log filtering, metric reduction, storage tiering), Excellent problem-solving, debugging, and collaboration skills in complex cloud-native environments", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "## Accountabilities Design and implement end-to-end observability architectures using OpenTelemetry, Prometheus, Grafana, and related tools across cloud environments. Build and maintain centralized observability pipelines across multi-account AWS environments, including CloudWatch, CloudTrail, and VPC Flow Logs. Develop scalable log aggregation and routing strategies, including filtering, noise reduction, and integration with systems such as Splunk HEC. Create advanced alerting frameworks and high-quality dashboards using Alertmanager, CloudWatch Alarms, and Grafana with PromQL. Deploy and manage observability infrastructure using Infrastructure as Code tools such as Terraform. Support Kubernetes and container-based observability across EKS and ECS environments. Optimize observability systems for performance, cost efficiency, and scalability in large-scale production environments. Collaborate with engineering teams to improve system reliability, monitoring standards, and incident response capabilities. Requirements: 8+ years of experience in DevOps, Site Reliability Engineering, or Observability Engineering roles. Strong hands-on experience designing unified observability pipelines using OpenTelemetry, Prometheus, and Grafana. Deep expertise in AWS observability services including CloudWatch, CloudTrail, and cross-account telemetry strategies. Proven ability to build and manage large-scale log aggregation systems and optimize high-volume data pipelines. Strong experience with Kubernetes (EKS) or containerized environments (ECS) in production settings. Advanced proficiency with Terraform or other Infrastructure as Code tools for infrastructure and observability deployments. Experience building alerting systems, dashboards, and monitoring frameworks for distributed systems. Strong understanding of cost optimization strategies for observability platforms (log filtering, metric reduction, storage tiering). Excellent problem-solving, debugging, and collaboration skills in complex cloud-native environments. Benefits: Competitive compensation aligned with experience and market benchmarks. Remote work flexibility within United States. Opportunity to work on large-scale, AI-driven, cloud-native infrastructure systems. Exposure to enterprise clients and high-impact digital transformation projects. Hands-on experience with leading observability and cloud technologies in production environments. Strong learning and upskilling culture in AI, cloud, and platform engineering. Collaborative, high-performance engineering environment focused on innovation and reliability. Opportunity to shape next-generation observability practices at scale. ## Additional Information How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1", "summaryDescription" : "DevOps/Observability Engineer. Skills: Observability, DevOps, AWS, Kubernetes. Design and implement end-to-end observability architectures. Build and maintain centralized observability pipelines", "postedDate" : "2026-06-15T08:26:25.600", "createdAt" : "2026-06-15T08:26:25.600", "lastUpdated" : "2026-06-16T11:07:52.421", "ingestTimestamp" : "2026-06-16T03:20:46.097", "mongoId" : "6a305118f292fd229cef9890", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "75k-100k", "hasSalary" : false, "allSkills" : [ "Observability architectures", "Log aggregation", "Alerting frameworks", "Infrastructure as Code", "Container orchestration", "Observability", "DevOps", "AWS", "Kubernetes", "System design", "Cost optimization", "Performance optimization", "Cloud environments", "Multi-account AWS", "Distributed systems", "Cloud-native environments", "OpenTelemetry", "Prometheus", "Grafana", "CloudWatch", "CloudTrail", "Splunk HEC", "Alertmanager", "Terraform" ], "skillCount" : 24, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a305118f292fd229cef988e", "title" : "DevOps/Observability Engineer", "industry" : "IT", "salary" : { "min" : 120000.0, "max" : 180000.0, "currency" : "EUR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior DevOps/Observability Engineer in Bulgaria, adjusted for executive seniority and full-time employment." }, "location" : "Canada", "locations" : [ "Canada" ], "timestamp" : "2026-06-16T11:48:45.432", "fingerprint" : "20ea23076aaa59286c631ffb406d89a97e7f7142c10ee757dc86b8b7e2712eaf", "source" : "lever", "language" : "en", "applyUrl" : "https://jobs.lever.co/jobgether/4cb8a5de-4a0a-42e4-af5b-b2fad9c41107/apply", "externalId" : "4cb8a5de-4a0a-42e4-af5b-b2fad9c41107", "industryFunction" : { }, "structuredLocations" : [ { "country" : "Bulgaria", "continent" : "eu", "workMode" : "remote" } ], "locationText" : "Bulgaria", "employmentType" : "FULL_TIME", "experienceMinYears" : 8, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "OpenTelemetry, Prometheus, Grafana, CloudWatch, CloudTrail, VPC Flow Logs, Splunk HEC, Alertmanager, CloudWatch Alarms, PromQL, Terraform, Kubernetes, EKS, ECS", "professionalSkills" : [ "System design", "Cost optimization", "Performance optimization", "Scalability optimization" ], "hardSkillsList" : [ "Observability architecture", "Log aggregation", "Infrastructure as Code", "Alerting frameworks", "Dashboard creation", "Container orchestration" ], "softSkillsList" : [ "Problem-solving" ], "hardSkills" : [ { "name" : "Observability architecture", "level" : "intermediate" }, { "name" : "Log aggregation", "level" : "intermediate" }, { "name" : "Infrastructure as Code", "level" : "intermediate" }, { "name" : "Alerting frameworks", "level" : "intermediate" }, { "name" : "Dashboard creation", "level" : "intermediate" }, { "name" : "Container orchestration", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Problem-solving" } ], "majorSkills" : "Observability, DevOps, AWS, Kubernetes", "majorSkillsList" : [ "Observability", "DevOps", "AWS", "Kubernetes" ], "coreResponsibilities" : "Design observability architectures, Implement observability architectures, Build observability pipelines, Maintain observability pipelines, Develop log aggregation strategies, Develop log routing strategies, Filter logs, Reduce log noise, Integrate with systems, Create alerting frameworks, Create high-quality dashboards, Deploy observability infrastructure, Manage observability infrastructure, Support Kubernetes observability, Support container-based observability, Optimize observability systems, Collaborate with engineering teams, Improve system reliability, Improve monitoring standards, Improve incident response capabilities", "teamCollaboration" : "Engineering teams", "domainKnowledge" : "Cloud environments; Multi-account AWS; Distributed systems; Cloud-native environments", "domainList" : [ "cloud-environments", "multi-account-aws", "distributed-systems", "cloud-native-environments" ], "domainSpecificKnowledge" : [ "Cloud environments", "Multi-account AWS", "Distributed systems", "Cloud-native environments" ], "toolProficiency" : [ "OpenTelemetry", "Prometheus", "Grafana", "CloudWatch", "CloudTrail", "Splunk HEC", "Alertmanager", "Terraform", "EKS", "ECS" ], "continuousLearning" : "AI; Cloud; Platform engineering", "innovationCreativity" : "Innovation", "problemSolvingSkills" : "Problem-solving; Debugging", "qualificationsBasic" : "8+ years of experience, Hands-on experience designing unified observability pipelines, Deep expertise in AWS observability services, Proven ability to build and manage large-scale log aggregation systems, Experience with Kubernetes (EKS) or containerized environments (ECS), Advanced proficiency with Terraform or other Infrastructure as Code tools, Experience building alerting systems, dashboards, and monitoring frameworks", "qualificationsPreferred" : "Understanding of cost optimization strategies", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "## Accountabilities Design and implement end-to-end observability architectures using OpenTelemetry, Prometheus, Grafana, and related tools across cloud environments. Build and maintain centralized observability pipelines across multi-account AWS environments, including CloudWatch, CloudTrail, and VPC Flow Logs. Develop scalable log aggregation and routing strategies, including filtering, noise reduction, and integration with systems such as Splunk HEC. Create advanced alerting frameworks and high-quality dashboards using Alertmanager, CloudWatch Alarms, and Grafana with PromQL. Deploy and manage observability infrastructure using Infrastructure as Code tools such as Terraform. Support Kubernetes and container-based observability across EKS and ECS environments. Optimize observability systems for performance, cost efficiency, and scalability in large-scale production environments. Collaborate with engineering teams to improve system reliability, monitoring standards, and incident response capabilities. Requirements: 8+ years of experience in DevOps, Site Reliability Engineering, or Observability Engineering roles. Strong hands-on experience designing unified observability pipelines using OpenTelemetry, Prometheus, and Grafana. Deep expertise in AWS observability services including CloudWatch, CloudTrail, and cross-account telemetry strategies. Proven ability to build and manage large-scale log aggregation systems and optimize high-volume data pipelines. Strong experience with Kubernetes (EKS) or containerized environments (ECS) in production settings. Advanced proficiency with Terraform or other Infrastructure as Code tools for infrastructure and observability deployments. Experience building alerting systems, dashboards, and monitoring frameworks for distributed systems. Strong understanding of cost optimization strategies for observability platforms (log filtering, metric reduction, storage tiering). Excellent problem-solving, debugging, and collaboration skills in complex cloud-native environments. Benefits: Competitive compensation aligned with experience and market benchmarks. Remote work flexibility within Canada. Opportunity to work on large-scale, AI-driven, cloud-native infrastructure systems. Exposure to enterprise clients and high-impact digital transformation projects. Hands-on experience with leading observability and cloud technologies in production environments. Strong learning and upskilling culture in AI, cloud, and platform engineering. Collaborative, high-performance engineering environment focused on innovation and reliability. Opportunity to shape next-generation observability practices at scale. ## Additional Information How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1", "summaryDescription" : "DevOps/Observability Engineer. Skills: Observability, DevOps, AWS, Kubernetes. Design observability architectures. Implement observability architectures", "postedDate" : "2026-06-15T08:25:46.131", "createdAt" : "2026-06-15T08:25:46.131", "lastUpdated" : "2026-06-16T11:48:45.432", "ingestTimestamp" : "2026-06-16T03:20:46.910", "mongoId" : "6a305118f292fd229cef988e", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "100k-150k", "hasSalary" : false, "allSkills" : [ "Observability architecture", "Log aggregation", "Infrastructure as Code", "Alerting frameworks", "Dashboard creation", "Container orchestration", "Problem-solving", "Observability", "DevOps", "AWS", "Kubernetes", "System design", "Cost optimization", "Performance optimization", "Scalability optimization", "Cloud environments", "Multi-account AWS", "Distributed systems", "Cloud-native environments", "OpenTelemetry", "Prometheus", "Grafana", "CloudWatch", "CloudTrail", "Splunk HEC", "Alertmanager", "Terraform", "EKS", "ECS" ], "skillCount" : 29, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Executive", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2c6a5b74d8ee00a090b73c", "title" : "Monitoring Engineer", "company" : "Adyen", "industry" : "FinTech", "salary" : { "min" : 135000.0, "max" : 185000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for a Mid-level Monitoring Engineer in San Francisco, United States, with adjustments for the FinTech industry and company size." }, "location" : "San Francisco", "locations" : [ "San Francisco" ], "timestamp" : "2026-06-15T05:04:15.823", "fingerprint" : "d60a694950d610340bd91fa874b11e5bf7f8f280b1f09df5cd333e0b37bbc7ae", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.greenhouse.io/adyen/jobs/7939051", "externalId" : "7939051", "industryFunction" : { }, "structuredLocations" : [ { "city" : "San Francisco", "state" : "California", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "37.7879363,-122.4075201" } ], "locationText" : "San Francisco, California, United States", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "This is Adyen Adyen provides payments, data, and financial products in a single solution for customers like Meta, Uber, H we do not offer remote-only roles.", "summaryDescription" : "Monitoring Engineer at Adyen", "postedDate" : "2026-06-14T08:03:17.296", "createdAt" : "2026-06-14T08:03:17.296", "lastUpdated" : "2026-06-15T05:04:15.823", "ingestTimestamp" : "2026-06-14T08:03:17.296", "mongoId" : "6a2c6a5b74d8ee00a090b73c", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 135000, "salaryAnnualMax" : 185000, "salaryBand" : "100k-150k", "hasSalary" : true, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Mid", "dataQualityScore" : 0.6666667, "daysOld" : 0, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "FinTech", "llmIndustryConfidence" : 0.95 }, { "id" : "69ce5e3b9bc74574cb677a91", "title" : "SRE - Observability Expert", "industry" : "Technology", "salary" : { "min" : 2200000.0, "max" : 3500000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Mid-level SRE - Observability Expert in Bangalore, India, adjusted for the technology industry and full-time employment." }, "location" : "India-Karnataka-Bangalore", "locations" : [ "India-Karnataka-Bangalore", "Brigade Tech Gardens, Katha No. 119, Kundalahalli Village, K.R. Puram Hobli, Ward No. 85, Bangalore" ], "timestamp" : "2026-06-15T04:51:58.142", "fingerprint" : "01d3dd8ea057dbf2663712ad96904bea4681f8b8fb4c5cb6381335d552aee722", "source" : "taleo", "language" : "en", "applyUrl" : "https://daimler.taleo.net/careersection/ex/jobdetail.ftl?job=869544", "externalId" : "869544", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Bangalore", "state" : "Karnataka", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "12.9767936,77.5900820" } ], "locationText" : "Bangalore, Karnataka, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 4, "experienceMaxYears" : 6, "experienceLevel" : "Mid", "technicalSkills" : "AWS, Azure, Terraform, Kubernetes, AKS, Databricks, Azure Data Factory, Amazon data Pipeline, Apache Spark, Kafka, Confluent cloud, Apache Storm, Spark-Streaming, Apache Flink, Kstreams App, KSQL, Event Hubs, ADLS2, REST APIs, Airflow, Druid, OpenSearch, Superset, Python, FastAPI, Git", "professionalSkills" : [ "Infrastructure-as-code", "Data pipeline orchestration", "Stream processing", "Batch processing", "Storage strategy", "Data transformation", "Data ingestion", "Data distribution", "API development", "Managed services", "Auto-scaling", "High availability", "Elasticity", "Networking", "Federated access", "Access controls", "Multi-tenancy", "Self-service tooling", "Data catalog management", "Technology research", "Platform capabilities" ], "hardSkillsList" : [ "Production development", "Production operations", "Infrastructure deployment", "Data processing", "Data accessibility", "Data availability", "Cloud cost", "Scripting", "Automation", "Integration tasks", "API deployment", "Cloud computing", "Branching strategies", "Merging strategies", "Pull Requests", "Command line functions", "DevSecOps practices", "Day 2 Ops" ], "hardSkills" : [ { "name" : "Production development", "level" : "intermediate" }, { "name" : "Production operations", "level" : "intermediate" }, { "name" : "Infrastructure deployment", "level" : "intermediate" }, { "name" : "Data processing", "level" : "intermediate" }, { "name" : "Data accessibility", "level" : "intermediate" }, { "name" : "Data availability", "level" : "intermediate" }, { "name" : "Cloud cost", "level" : "intermediate" }, { "name" : "Scripting", "level" : "intermediate" }, { "name" : "Automation", "level" : "intermediate" }, { "name" : "Integration tasks", "level" : "intermediate" }, { "name" : "API deployment", "level" : "intermediate" }, { "name" : "Cloud computing", "level" : "intermediate" }, { "name" : "Branching strategies", "level" : "intermediate" }, { "name" : "Merging strategies", "level" : "intermediate" }, { "name" : "Pull Requests", "level" : "intermediate" }, { "name" : "Command line functions", "level" : "intermediate" }, { "name" : "DevSecOps practices", "level" : "intermediate" }, { "name" : "Day 2 Ops", "level" : "intermediate" } ], "majorSkills" : "Observability, Infrastructure-as-code, Kubernetes, Data pipelines", "majorSkillsList" : [ "Observability", "Infrastructure-as-code", "Kubernetes", "Data pipelines" ], "coreResponsibilities" : "Develop infrastructure-as-code, Maintain infrastructure-as-code, Deploy Kubernetes clusters, Manage Databricks environments, Orchestrate data pipelines, Process streams, Process batches, Architect storage strategy, Transform data, Ingest data, Distribute data, Set-up open-source stack, Manage open-source stack, Script for automation, Script for integration, Build APIs, Deploy APIs, Handle managed services, Handle IAM, Handle auto-scaling, Handle high availability, Handle elasticity, Handle networking options, Handle federated access, Manage access controls, Manage data catalog, Research new technologies, Investigate new technologies, Evolve data platform capabilities", "teamCollaboration" : "Agile scrum Methodologies", "projectManagementSkills" : [ "Agile", "Scrum" ], "domainKnowledge" : "Data ingestion; Data streaming; Data transformation; Data analytics; Data lake storage; Self-service compute; ML workspaces; Data pipelines; Kappa architecture; Multi-tenancy; DevSecOps practices", "domainList" : [ "data-ingestion", "data-streaming", "data-transformation", "data-analytics", "data-lake-storage", "self-service-compute", "ml-workspaces", "data-pipelines", "kappa-architecture", "multi-tenancy", "devsecops-practices" ], "domainSpecificKnowledge" : [ "Data ingestion", "Data streaming", "Data transformation", "Data analytics", "Data lake storage", "Self-service compute", "ML workspaces", "Data pipelines", "Kappa architecture", "Multi-tenancy", "DevSecOps practices" ], "toolProficiency" : [ "Terraform", "Kubernetes", "AKS", "Databricks", "Azure Data Factory", "Amazon data Pipeline", "Apache Spark", "Kafka", "Confluent cloud", "Apache Storm", "Spark-Streaming", "Apache Flink", "Kstreams App", "KSQL", "Event Hubs", "ADLS2", "REST APIs", "Airflow", "Druid", "OpenSearch", "Superset", "Python", "FastAPI", "Git", "Datadog" ], "continuousLearning" : "Research new technologies; Investigate new technologies", "innovationCreativity" : "Bring new technologies", "problemSolvingSkills" : "Root cause analysis", "qualificationsBasic" : "4-6 years production experience, AWS or Azure Cloud experience", "qualificationsPreferred" : "Experience architecting storage strategy, Experience with Kstreams App/KSQL/Processor Libraries, Experience with managed connectors, Experience with Event Hubs, Experience with kafka topics, Experience with ADLS2, Experience with REST APIs, Experience with Airflow, Experience with Druid, Experience with Kafka (open source), Experience with OpenSearch, Experience with Superset, Experience with Python scripting, Experience with FastAPI, Experience with managed services, Experience with IAM, Experience with auto-scaling, Experience with High availability, Experience with elasticity, Experience with networking options, Experience with federated access, Experience with Git, Experience with DevSecOps practices, Experience with Datadog", "remoteFriendly" : false, "rawDescription" : "Data Infrastructure & Operations Offer flexible and secure data ingestion, streaming, transformation, analytics and data lake storage paired with self-service compute & ML workspaces so that In-house data teams can spin-up services and create pipelines as per their business requirements Job description · Looking for 4-6 years of hand-ons experience with production-level development and operations on AWS or Azure Cloud · Develop and maintain infrastructure-as-code using Terraform to deploy and manage Kubernetes clusters (AKS) and Databricks environments · Hands-on experience with data pipeline orchestration tools like Azure Data Factory, Amazon data Pipeline, Apache Spark, Databricks · Hands-on experience with one or more of stream & batch processing systems: Kafka (Confluent cloud, open source), Apache Storm, Spark-Streaming, Apache Flink, Kappa architecture · Experience in architecting right storage strategy for use-cases, keeping data processing, data accessibility, data availability and cloud cost considerations · Proficiency in Data transformation using Kstreams App/KSQL/Processor Libraries · Data ingestion and data distribution integration experience using managed connectors such as Event Hubs, kafka topics, ADLS2, REST APIs · Proficiency to set-up & manage open-source stack, including Airflow, Druid, Kafka (open source) OpenSearch, and Superset · Proficiency in Python scripting for automation and integration tasks · Utilize FastAPI for building and deploying high-performance APIs · Handling requirements of managed services, IAM, auto-scaling, High availability, elasticity, networking options · Handle federated access to cloud computing resource (or set of resources) based on a user's role within the organization · Proficiency with Git, including branching/merging strategies, Pull Requests, and basic command line functions · Proficiency in DevSecOps practices throughout the product lifecycle including fully managed Day 2 Ops leveraging Datadog · Shared access controls to support multi-tenancy and self-service tooling for customers · Manage data catalog per topic or domain based on services & use-cases offered · Research, investigate and bring new technologies to continually evolve data platform capabilities · Experience in working under Agile scrum Methodologies Data Infrastructure & Operations Offer flexible and secure data ingestion, streaming, transformation, analytics and data lake storage paired with self-service compute & ML workspaces so that In-house data teams can spin-up services and create pipelines as per their business requirements Job description · Looking for 4-6 years of hand-ons experience with production-level development and operations on AWS or Azure Cloud · Develop and maintain infrastructure-as-code using Terraform to deploy and manage Kubernetes clusters (AKS) and Databricks environments · Hands-on experience with data pipeline orchestration tools like Azure Data Factory, Amazon data Pipeline, Apache Spark, Databricks · Hands-on experience with one or more of stream & batch processing systems: Kafka (Confluent cloud, open source), Apache Storm, Spark-Streaming, Apache Flink, Kappa architecture · Experience in architecting right storage strategy for use-cases, keeping data processing, data accessibility, data availability and cloud cost considerations · Proficiency in Data transformation using Kstreams App/KSQL/Processor Libraries · Data ingestion and data distribution integration experience using managed connectors such as Event Hubs, kafka topics, ADLS2, REST APIs · Proficiency to set-up & manage open-source stack, including Airflow, Druid, Kafka (open source) OpenSearch, and Superset · Proficiency in Python scripting for automation and integration tasks · Utilize FastAPI for building and deploying high-performance APIs · Handling requirements of managed services, IAM, auto-scaling, High availability, elasticity, networking options · Handle federated access to cloud computing resource (or set of resources) based on a user's role within the organization · Proficiency with Git, including branching/merging strategies, Pull Requests, and basic command line functions · Proficiency in DevSecOps practices throughout the product lifecycle including fully managed Day 2 Ops leveraging Datadog · Shared access controls to support multi-tenancy and self-service tooling for customers · Manage data catalog per topic or domain based on services & use-cases offered · Research, investigate and bring new technologies to continually evolve data platform capabilities · Experience in working under Agile scrum Methodologies Mercedes-Benz Research and Development India Private Limited", "summaryDescription" : "SRE - Observability Expert. Skills: Observability, Infrastructure-as-code, Kubernetes, Data pipelines. Develop infrastructure-as-code. Maintain infrastructure-as-code", "createdAt" : "2026-06-14T00:40:16.356", "lastUpdated" : "2026-06-15T04:51:58.142", "ingestTimestamp" : "2026-06-14T00:40:16.356", "mongoId" : "69ce5e3b9bc74574cb677a91", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ "Production development", "Production operations", "Infrastructure deployment", "Data processing", "Data accessibility", "Data availability", "Cloud cost", "Scripting", "Automation", "Integration tasks", "API deployment", "Cloud computing", "Branching strategies", "Merging strategies", "Pull Requests", "Command line functions", "DevSecOps practices", "Day 2 Ops", "Observability", "Infrastructure-as-code", "Kubernetes", "Data pipelines", "Data pipeline orchestration", "Stream processing", "Batch processing", "Storage strategy", "Data transformation", "Data ingestion", "Data distribution", "API development", "Managed services", "Auto-scaling", "High availability", "Elasticity", "Networking", "Federated access", "Access controls", "Multi-tenancy", "Self-service tooling", "Data catalog management", "Technology research", "Platform capabilities", "Agile", "Scrum", "Data streaming", "Data analytics", "Data lake storage", "Self-service compute", "ML workspaces", "Kappa architecture", "Terraform", "AKS", "Databricks", "Azure Data Factory", "Amazon data Pipeline", "Apache Spark", "Kafka", "Confluent cloud", "Apache Storm", "Spark-Streaming", "Apache Flink", "Kstreams App", "KSQL", "Event Hubs", "ADLS2", "REST APIs", "Airflow", "Druid", "OpenSearch", "Superset", "Python", "FastAPI", "Git", "Datadog" ], "skillCount" : 74, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Mid", "dataQualityScore" : 0.7777778, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2ab39a74d8ee00a06d65b0", "title" : "Senior Software Engineer, Logging & Experiments", "company" : "Asana", "industry" : "Technology", "salary" : { "min" : 145000.0, "max" : 205000.0, "currency" : "CAD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for Senior Software Engineer in Vancouver, Canada, adjusted for the technology industry and company size." }, "location" : "Vancouver, British Columbia, Canada", "locations" : [ "Vancouver", "British Columbia", "Canada" ], "timestamp" : "2026-06-14T22:17:59.597", "fingerprint" : "2d92ba8d71ec64e9c687781b482f41472bb7a4732868e657d8507c0ee4343091", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://www.asana.com/jobs/apply/7964326?gh_jid=7964326", "externalId" : "7964326", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Vancouver", "state" : "British Columbia", "country" : "Canada", "continent" : "na", "source" : "llm", "workMode" : "hybrid", "geo" : "49.2608724,-123.1139520" } ], "locationText" : "Vancouver, British Columbia, Canada", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Logging, Experiments, Data processing, Observability, Logging platforms", "professionalSkills" : [ "System design", "Operational excellence" ], "hardSkillsList" : [ "Data-driven decisions" ], "softSkillsList" : [ "Mentorship" ], "hardSkills" : [ { "name" : "Data-driven decisions", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Mentorship" } ], "majorSkills" : "Logging systems, Experimentation frameworks", "majorSkillsList" : [ "Logging systems", "Experimentation frameworks" ], "coreResponsibilities" : "Design logging and experimentation projects, Develop logging and experimentation projects, Maintain logging and experimentation projects, Scale experimentation framework, Optimize experimentation framework, Define logging APIs, Implement logging APIs, Curate observability experience, Collaborate with Product teams, Collaborate with Infrastructure teams, Collaborate with Data Science teams, Write design docs, Write documentation", "teamCollaboration" : "Cross-functional teams; Product teams; Infrastructure teams; Data Science teams", "domainKnowledge" : "Data Infrastructure; Backend-oriented; High-bandwidth logging; Feature flagging; Data contracts; Observability challenges; Cloud-native infrastructure; Distributed systems", "domainList" : [ "data-infrastructure", "backend-oriented", "high-bandwidth-logging", "feature-flagging", "data-contracts", "observability-challenges", "cloud-native-infrastructure", "distributed-systems" ], "domainSpecificKnowledge" : [ "Data Infrastructure", "Backend-oriented", "High-bandwidth logging", "Feature flagging", "Data contracts", "Observability challenges", "Cloud-native infrastructure", "Distributed systems" ], "communicationSkills" : "Technical clarity", "documentationSkills" : "Design docs; Documentation", "continuousLearning" : "Leverage AI tools", "problemSolvingSkills" : "Solve hard technical challenges; Solving problems across the stack", "outcomesObjectives" : "Empower data-driven decisions", "qualificationsBasic" : "5+ years of experience designing and shipping production-ready systems, Experience shipping production-grade code, Experience navigating application development, Experience navigating data-intensive backends, Focus on building scalable backend services, Focus on building distributed systems, Focus on building cloud-native infrastructure", "qualificationsPreferred" : "Familiarity with distributed data processing, Familiarity with experiment and feature flag rollout systems, Familiarity with modern observability and logging platforms, Interest to learn distributed data processing, Interest to learn experiment and feature flag rollout systems, Interest to learn modern observability and logging platforms", "remoteFriendly" : true, "workSiteFlexibility" : "Hybrid", "rawDescription" : "We’re looking for a backend-oriented senior engineer to join our Data Infrastructure team in Vancouver to scale the foundation of how Asana measures success. The Data Infrastructure team builds the infrastructure responsible for consuming, exposing, and creating product and product-derived datasets, owning the pipelines that transport and process data from all of Asana’s product surfaces. You will lead the design and execution of high-bandwidth logging systems and experimentation frameworks that empower every product team at Asana to make data-driven decisions. As a senior member of the team, you’ll solve hard technical challenges and magnify the impact of those around you through mentorship and operational excellence. This role is based in our Vancouver office with an office-centric hybrid schedule. The standard in-office days are Monday, Tuesday, and Thursday. Most Asanas have the option to work from home on Wednesdays. Working from home on Fridays depends on the type of work you do and the teams with which you partner. If you're interviewing for this role, your recruiter will share more about the in-office requirements. What you’ll achieve Design, develop, and maintain medium to large-scale projects related to logging and experimentation, acting as a subject matter expert for our Vancouver engineering site. Scale and optimize our in-house experimentation and feature flagging framework, ensuring reliable, low-latency execution for logic sitting in the critical path of every Asana user session. Define and implement the next generation of our logging APIs, establishing the high-fidelity data contracts used across the company to architect solutions for unique observability challenges. Curate the observability experience for Asana’s engineers, working at the interface of vendor capabilities and internal workflows to provide out-of-the-box monitoring and debugging. Collaborate cross-functionally with Product, Infrastructure, and Data Science teams to align our infrastructure with the evolving needs of Asana’s strategy. Facilitate technical clarity across teams by writing high-quality design docs and documentation that scale your impact beyond your immediate projects. About you Software, Data, or Infrastructure Engineering background with experience shipping production-grade code and navigating both application development and data-intensive backends. 5+ years of experience designing and shipping production-ready systems, with a focus on building scalable backend services, distributed systems, or cloud-native infrastructure. Familiarity with at least one of the following, or a strong interest to learn: distributed data processing, experiment and feature flag rollout systems, and modern observability and logging platforms. Demonstrates curiosity about AI tools and emerging technologies, with a willingness to learn and leverage them to enhance productivity, collaboration, or decision-making. Strong focus on competencies such as solving problems across the stack and participating in complex infrastructure rollouts. What we’ll offer Our comprehensive compensation package plays a big part in how we recognize you for the impact you have on our path to achieving our mission. We believe that compensation should be reflective of the value you create relative to the market value of your role. To ensure pay is fair and not impacted by biases, we're committed to looking at market value which is why we check ourselves and conduct a yearly pay equity audit. For this role, the estimated base salary range is between $176,000 - $200,000. The actual base salary will vary based on various factors, including market and individual qualifications objectively assessed during the interview process. The listed range above is a guideline, and the base salary range for this role may be modified. In addition to base salary, your compensation package may include additional components such as equity, sales incentive pay (for most sales roles), and benefits. If you're interviewing for this role, speak with your recruiter to learn more about the total compensation and benefits for this role. We strive to provide equitable and competitive benefits packages that support our employees worldwide and include: Mental health, wellness & fitness benefits Career coaching & support Inclusive family building benefits Long-term savings or retirement plans In-office culinary options to cater to your dietary preferences #LI-Hybrid #LI-HC1 About us Asana is a leading platform for human + AI collaboration. Millions of teams around the world rely on Asana to achieve their most important goals, faster. Asana has been named to Fortune's Best Workplaces for 7+ years and recognized by Fast Company, Forbes, and Gartner for excellence in workplace culture and innovation. We offer an exceptional office-centric culture while adopting the best elements of hybrid models to ensure that every one of our global team members can work together effortlessly. With 13+ offices all over the world, we are always looking for individuals who care about building technology that drives positive change in the world and a culture where everyone feels that they belong. Join Asana’s Talent Network to stay up to date on job opportunities and life at Asana.", "summaryDescription" : "Senior Software Engineer, Logging & Experiments at Asana. Skills: Logging systems, Experimentation frameworks. Design logging and experimentation projects. Develop logging and experimentation projects", "postedDate" : "2026-06-11T19:18:47.479", "createdAt" : "2026-06-11T19:18:47.479", "lastUpdated" : "2026-06-14T22:17:59.597", "ingestTimestamp" : "2026-06-11T19:18:47.479", "mongoId" : "6a2ab39a74d8ee00a06d65b0", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "100k-150k", "hasSalary" : false, "allSkills" : [ "Data-driven decisions", "Mentorship", "Logging systems", "Experimentation frameworks", "System design", "Operational excellence", "Data Infrastructure", "Backend-oriented", "High-bandwidth logging", "Feature flagging", "Data contracts", "Observability challenges", "Cloud-native infrastructure", "Distributed systems" ], "skillCount" : 14, "jobCategory" : "engineering", "jobSubcategory" : "product-engineering", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology" }, { "id" : "69cf26132beec4dd3d90b57d", "title" : "Cardiac Monitoring Tech - Central Monitoring Unit", "company" : "Tampa General Hospital", "industry" : "Healthcare", "salary" : { "min" : 38000.0, "max" : 52000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline data for an Entry-level Cardiac Monitoring Tech in Tampa, FL, adjusted for the healthcare industry and a large hospital system." }, "location" : "United States-Florida-Tampa", "locations" : [ "United States-Florida-Tampa", "
TGH Main Campus (TGHMAIN)
1 Tampa General Circle

Tampa, 33601

" ], "certifications" : [ "EKG certification" ], "timestamp" : "2026-06-15T09:54:24.883", "fingerprint" : "0693b3c24ecb2e2a2708d28cc088b299c75c1d5cfee103fbd903f356e5e16ebe", "source" : "taleo", "language" : "en", "applyUrl" : "https://tgh.taleo.net/careersection/ex/jobdetail.ftl?job=674718", "externalId" : "674718", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Tampa", "state" : "Florida", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "27.9449854,-82.4583107" } ], "locationText" : "Tampa, Florida, United States", "minimumEducation" : "High School", "domainKnowledge" : "Basic normal cardiac rhythms; Dysrhythmias; Lethal rhythms", "domainList" : [ "basic-normal-cardiac-rhythms", "dysrhythmias", "lethal-rhythms" ], "domainSpecificKnowledge" : [ "Basic normal cardiac rhythms", "Dysrhythmias", "Lethal rhythms" ], "communicationSkills" : "Verbal communication; Written communication", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "Under general supervision, follows established policies, procedures and professional guidelines. Responsible for monitoring and identifying basic normal cardiac rhythms, dysrhythmias and lethal arrhythmias; reporting these findings to the appropriate personnel, and rhythm documentation and labeling per TGH policy. Performs customer service, receptionist and clerical/ secretarial activities. Serves as a communication resource for patients, visitors, family, and health care team members with the ability to triage communication priorities. Answers the telephone and patient intercom system. Alerts nursing staff to patient and family concerns and other calls, orders supplies and stock items as required. Dual role responsibilities will not be performed at the same time, but will be able to flex between the roles based on organizational needs. Also responsible for performing job duties in accordance with mission, vision and values of Tampa General Hospital. table {mso-displayed-decimal-separator:\"\\.\"; mso-displayed-thousand-separator:\"\\,\";} tr {mso-height-source:auto;} col {mso-width-source:auto;} td {padding-top:1px; padding-right:1px; padding-left:1px; mso-ignore:padding; color:black; font-size:11.0pt; font-weight:400; font-style:normal; text-decoration:none; font-family:Calibri, sans-serif; mso-font-charset:0; text-align:general; vertical-align:bottom; border:none; white-space:nowrap; mso-rotate:0;} .font7 {color:black; font-size:11.0pt; font-weight:400; font-style:normal; text-decoration:none; font-family:\"Times New Roman\", serif; mso-font-charset:0;} .font11 {color:black; font-size:11.0pt; font-weight:700; font-style:normal; text-decoration:none; font-family:\"Times New Roman\", serif; mso-font-charset:0;} .xl418 {font-family:\"Times New Roman\", serif; mso-font-charset:0; text-align:left; vertical-align:top; white-space:normal;} High school diploma or GED required. Successful completion of EKG certification program or previous experience as a Monitor Technician in an acute care hospital and successful completion of a competency assessment required. Ability to accurately interpret rhythm strips and recognize changes required. Ability to demonstrate knowledge of basic computer skills, medical terminology and communicates effectively both verbally and in writing required. Can be a licensed Paramedic in Florida or a nationally recognized Paramedic. Tampa", "summaryDescription" : "Cardiac Monitoring Tech - Central Monitoring Unit at Tampa General Hospital", "createdAt" : "2026-06-14T06:45:32.694", "lastUpdated" : "2026-06-15T09:54:24.883", "ingestTimestamp" : "2026-06-14T06:45:32.694", "mongoId" : "69cf26132beec4dd3d90b57d", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 38000, "salaryAnnualMax" : 52000, "salaryBand" : "30k-50k", "hasSalary" : true, "allSkills" : [ "Basic normal cardiac rhythms", "Dysrhythmias", "Lethal rhythms", "EKG certification" ], "skillCount" : 4, "jobCategory" : "operations", "jobSubcategory" : "general", "seniorityLevel" : "Entry", "dataQualityScore" : 0.6666667, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Healthcare", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2c7e2974d8ee00a0951bb2", "title" : "Condition Monitoring Engineer", "company" : "AssetWatch, Inc.", "industry" : "Manufacturing", "salary" : { "min" : 72000.0, "max" : 108000.0, "currency" : "EUR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for Bulgaria, adjusted for senior level and remote work in the manufacturing industry." }, "location" : "Toronto, Ontario, Canada", "locations" : [ "Toronto", "Ontario", "Canada", "United States" ], "certifications" : [ "ISO Category II vibration certification" ], "timestamp" : "2026-06-16T04:32:47.399", "fingerprint" : "21ee813db7436a944512ecac7cf8d1dad8c53d260e13abddb9d8e9bf50743526", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.greenhouse.io/assetwatch/jobs/4698049005", "externalId" : "4698049005", "industryFunction" : { }, "structuredLocations" : [ { "country" : "Bulgaria", "continent" : "eu", "workMode" : "remote" } ], "locationText" : "Bulgaria", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Vibration analysis, Data analysis, Software modeling, Programming, Ultrasonic analysis, Oil analysis, Fluid analysis", "professionalSkills" : [ "Engineering evaluations" ], "hardSkillsList" : [ "Vibration data collection", "Data processing", "Machinery health evaluation", "Alarm level setting" ], "hardSkills" : [ { "name" : "Vibration data collection", "level" : "intermediate" }, { "name" : "Data processing", "level" : "intermediate" }, { "name" : "Machinery health evaluation", "level" : "intermediate" }, { "name" : "Alarm level setting", "level" : "intermediate" } ], "majorSkills" : "Condition monitoring, Vibration analysis, Predictive maintenance", "majorSkillsList" : [ "Condition monitoring", "Vibration analysis", "Predictive maintenance" ], "coreResponsibilities" : "Collect vibration and temperature data, Analyze vibration and temperature data, Customize data processing, Determine if maintenance is needed, Perform vibration data collection, Perform data analysis, Perform software modeling, Perform programming, Perform engineering evaluations, Evaluate machinery health and condition, Analyze vibration data, Develop software modeling, Develop programs, Maintain vibration data analysis library, Expand vibration data analysis library, Improve ability to process data, Provide actionable information to clients, Set appropriate alarm levels, Alert customers of pending failures, Accompany hardware installation team, Recommend placement of machine condition sensing units, Lead predictive maintenance tool develop program, Grow predictive maintenance tool develop program, Expand machine condition monitoring expertise, Include ultrasonic analysis, Include oil/fluid analysis, Create high-valued hardware solutions, Create high-valued software solutions, Create expanded product offerings", "teamCollaboration" : "Product development teams; Installation teams; Customer support teams; Customers' reliability engineers; Work collaboratively with others", "domainKnowledge" : "Machine condition monitoring; Industrial equipment; Predictive maintenance", "domainList" : [ "machine-condition-monitoring", "industrial-equipment", "predictive-maintenance" ], "domainSpecificKnowledge" : [ "Machine condition monitoring", "Industrial equipment", "Predictive maintenance" ], "toolProficiency" : [ "FFT analyzers", "Predictive maintenance software", "Microsoft Office Suite" ], "communicationSkills" : "Interpersonal skills", "problemSolvingSkills" : "Resolve obstacles", "specialRequirements" : "Work on elevated equipment", "outcomesObjectives" : "Generate high quality data; Generate actionable data; Generate high quality information; Generate actionable information", "qualificationsBasic" : "Five years of relevant experience, Vibration data collection and analysis, FFT analyzers, Predictive/preventative maintenance software, Technical competence, Electro-mechanical fundamentals, AC induction and DC motors, Industrial equipment mechanical background, Centrifugal and reciprocating compressors, Turbines, blowers, pumps, gearboxes, Hydraulics, pneumatics, Operation of one or more analyzers, Measuring vibration spectra and time waveforms, Developing optimum corrective actions, Acquired field vibration analysis data, Observations and discussions with key plant personnel, Work on and around elevated fixed and rotating equipment, Microsoft Office Suite proficiency, Standard PC applications proficiency", "qualificationsPreferred" : "ISO Category II vibration certification, Continued certification expected", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "AssetWatch serves global manufacturers by powering manufacturing uptime through the delivery of an unparalleled condition monitoring experience, with a passion to care about the assets our customers care for every day. We are a devoted and capable team that includes world-renowned engineers and distinguished business leaders united by a common goal – To build the future of predictive maintenance. As we enter the next phase of rapid growth, we are seeking people to help lead the journey. The primary function of the Condition Monitoring Engineer is supporting the company’s unique value proposition by generating high quality and actionable data and information for its industrial customers. This role works closely with product development, installation and customer support teams, as well as customers’ reliability engineers. In this role, you will: Collect and analyze vibration and temperature data at client sites, customizing data processing to the client’s asset and determining if maintenance is needed Perform vibration data collection, data analysis, software modeling and programming, and engineering evaluations Evaluate machinery health and condition, through detailed analysis of vibration data Develop software modeling and programs to maintain and expand vibration data analysis library to improve ability to process data Provide high-quality, actionable information to clients (e. g. setting appropriate alarm levels within the analytical tools to alert customers of pending failures). Accompany hardware installation team and recommend placement of machine condition sensing units. Lead and grow AssetWatch predictive maintenance (PdM) tool develop program Expand AssetWatch expertise in machine condition monitoring, beyond vibration analysis, to include ultrasonic analysis, oil/fluid analysis Work closely with the product development team to create high-valued hardware and software solutions and expanded product offerings Qualifications: Minimum of five years of relevant experience with vibration data collection and analysis, ideally using FFT analyzers and predictive/preventative maintenance software. (Must demonstrate technical competence.) Valid ISO Category II, or higher, vibration certification preferred. Continued certification expected. Strong understanding of electro-mechanical fundamentals, including AC induction and DC motors Strong mechanical background with industrial equipment - centrifugal and reciprocating compressors, turbines, blowers, pumps, gearboxes, hydraulics, pneumatics, etc. Proficient with the operation of one or more analyzers measuring vibration spectra and time waveforms. Proficient with developing optimum corrective actions based on findings of acquired field vibration analysis data, observations and discussions with key plant personnel. Must be able to work on and around elevated fixed and rotating equipment Proficiency with Microsoft Office Suite and standard PC applications. Good communication and interpersonal skills Desire to work in a “startup” environment and have a “startup” mentality – work collaboratively with others across all levels of the organization; resolve obstacles that may prevent the organization from achieving its mission; wear many hats as needed Be customer focused - demonstrate the desire and knowledge to understand customer needs; provide personalized, professional service, accurate information and continuous communication Demonstrate integrity - behave ethically, act fairly, and take responsibility for accomplishing work #LI-REMOTE What We Offer: AssetWatch is a remote-first company that puts people at the center of everything we do. We want our team members to thrive - that’s why we offer a range of benefits and perks designed to support your well-being, growth, and work-life balance. Competitive compensation package including stock options Flexible work schedule Comprehensive benefits including retirement plan match Opportunity to make a real impact every day Work with a dynamic and growing team Unlimited PTO We have a distributed team that works remotely across locations in the United States and Ontario, Canada. Collaboration within core working hours is required.", "summaryDescription" : "Condition Monitoring Engineer at AssetWatch, Inc.. Skills: Condition monitoring, Vibration analysis, Predictive maintenance. Collect vibration and temperature data. Analyze vibration and temperature data", "postedDate" : "2026-06-14T20:03:59.287", "createdAt" : "2026-06-14T20:03:59.287", "lastUpdated" : "2026-06-16T04:32:47.399", "ingestTimestamp" : "2026-06-14T20:03:59.287", "mongoId" : "6a2c7e2974d8ee00a0951bb2", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "50k-75k", "hasSalary" : false, "allSkills" : [ "Vibration data collection", "Data processing", "Machinery health evaluation", "Alarm level setting", "Condition monitoring", "Vibration analysis", "Predictive maintenance", "Engineering evaluations", "Machine condition monitoring", "Industrial equipment", "ISO Category II vibration certification", "FFT analyzers", "Predictive maintenance software", "Microsoft Office Suite" ], "skillCount" : 14, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Manufacturing", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2c6b6874d8ee00a09121f2", "title" : "Fleet Monitoring Technician", "company" : "EquipmentShare", "industry" : "Technology", "salary" : { "min" : 45000.0, "max" : 65000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Junior Fleet Monitoring Technician in Columbia, United States, adjusted for industry and company size." }, "location" : "Corporate", "locations" : [ "Corporate" ], "timestamp" : "2026-06-15T09:29:26.714", "fingerprint" : "709b85548d6d38875897f2fadd0c0027892118d1424f8195c6f3142ad49aa02c", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://www.equipmentshare.com/careers/openings/?gh_jid=8001682", "externalId" : "8001682", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Columbia", "state" : "Missouri", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "38.9518830,-92.3337366" } ], "locationText" : "Columbia, Missouri, United States", "employmentType" : "FULL_TIME", "minimumEducation" : "Associate's", "experienceMinYears" : 0, "experienceMaxYears" : 2, "experienceLevel" : "Entry", "technicalSkills" : "G-Suite, Gmail, Google Docs, Google Sheets, Google Drive", "professionalSkills" : [ "Process management", "Cross-functional coordination", "Vendor management", "Stakeholder management", "Operational metrics", "Resource planning", "Continuous improvement" ], "hardSkillsList" : [ "Incident triage", "Issue escalation", "Troubleshooting equipment issues", "Service maintenance intervals", "Customer queries", "Customer requests", "Case resolution", "Knowledge base documentation", "Technical knowledge", "Operational knowledge", "Critical alerts", "SLO performance", "SLA performance", "Team KPIs" ], "softSkillsList" : [ "Grit", "Heart", "Humility", "Energy", "Effort", "Optimism" ], "hardSkills" : [ { "name" : "Incident triage", "level" : "intermediate" }, { "name" : "Issue escalation", "level" : "intermediate" }, { "name" : "Troubleshooting equipment issues", "level" : "intermediate" }, { "name" : "Service maintenance intervals", "level" : "intermediate" }, { "name" : "Customer queries", "level" : "intermediate" }, { "name" : "Customer requests", "level" : "intermediate" }, { "name" : "Case resolution", "level" : "intermediate" }, { "name" : "Knowledge base documentation", "level" : "intermediate" }, { "name" : "Technical knowledge", "level" : "intermediate" }, { "name" : "Operational knowledge", "level" : "intermediate" }, { "name" : "Critical alerts", "level" : "intermediate" }, { "name" : "SLO performance", "level" : "intermediate" }, { "name" : "SLA performance", "level" : "intermediate" }, { "name" : "Team KPIs", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Grit" }, { "name" : "Heart" }, { "name" : "Humility" }, { "name" : "Energy" }, { "name" : "Effort" }, { "name" : "Optimism" } ], "majorSkills" : "Fleet monitoring, Incident management, Service delivery", "majorSkillsList" : [ "Fleet monitoring", "Incident management", "Service delivery" ], "coreResponsibilities" : "Perform job duties, Monitor fleet systems, Respond to events, Assist with incident triage, Assist with documentation, Assist with escalation, Support incident management process, Identify potential issues, Gather relevant information, Escalate issues as needed, Collaborate with support, Assist in troubleshooting, Resolve equipment issues, Coordinate with internal teams, Support issue resolution, Ensure timely communication, Support Uptime Management Center, Support internal teams, Ensure effective operations, Ensure service delivery, Monitor service maintenance intervals, Monitor branch personnel queries, Monitor customer queries, Respond to branch personnel requests, Respond to customer requests, Follow-up with branch personnel, Follow-up with customers, Ensure issues resolved, Close cases, Contribute to knowledge base, Support team learning, Improve efficiency, Participate in training initiatives, Support development, Enhance technical knowledge, Enhance operational knowledge, Work with dealerships, View critical alerts, Clear critical alerts, Adhere to contractual SLO, Adhere to contractual SLA, Support team KPIs, Represent department professionally, Interact with internal teams, Interact with customers", "teamCollaboration" : "Collaborate with Services Technical Support; Coordinate with internal teams; Support other members; Interactions with internal teams; Interactions with customers", "domainKnowledge" : "Heavy equipment; Mechanical systems; Fleet operations; Construction industry", "domainList" : [ "heavy-equipment", "mechanical-systems", "fleet-operations", "construction-industry" ], "domainSpecificKnowledge" : [ "Heavy equipment", "Mechanical systems", "Fleet operations", "Construction industry" ], "toolProficiency" : [ "T3 platform" ], "communicationSkills" : "Branch personnel queries; Customer queries; Branch personnel requests; Customer requests; Professional interactions", "documentationSkills" : "Incident documentation; Knowledge base documentation", "continuousLearning" : "Training initiatives; Professional development", "problemSolvingSkills" : "Incident triage; Troubleshooting; Issue resolution; Problem-solving", "specialRequirements" : "7x24 environment, Rotating shifts, Potential on-call schedule, Sit for prolonged periods, Work on a computer, Background check", "outcomesObjectives" : "Maintain fleet uptime; Maintain fleet performance; Ensure effective operations; Ensure service delivery; Resolve issues to satisfaction", "qualificationsBasic" : "Ability to maintain strict confidentiality, Organizational skills, Attention to detail and accuracy, Time management skills, Communication skills, Ability to leverage technology, Ability to multi-task, Manage multiple priorities, Ability to proofread and edit, Ability to be flexible, Adapt to change, Professional demeanor, Enthusiastic demeanor, Friendly demeanor", "qualificationsPreferred" : "Associate's degree preferred, Technical certification preferred, Trade school training preferred, Equivalent combination of education and experience preferred, 0-2 years customer support experience preferred, 0-2 years operation experience preferred, 0-2 years technical support experience preferred, 0-2 years related field experience preferred, Exposure to heavy equipment preferred, Exposure to mechanical systems preferred, Exposure to fleet operations preferred, Interest in coding preferred, Interest in scripting preferred, Interest in SQL querying preferred, Interest in database querying preferred", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "Build the Future with Us — EquipmentShare is Hiring a Fleet Monitoring Technician At EquipmentShare, we’re not just filling a role — we’re assembling the best team on the planet to build something that’s never been built before. We’re on a mission to transform an industry that’s been stuck in the past by empowering contractors and communities through innovative technology, real-time support, and a team that truly cares. We’re hiring a Fleet Monitoring Technician at our Corporate Headquarters in Columbia, MO, and we’re looking for someone who’s ready to grow with us, bring energy and drive to their work, and help us build the future of construction. The Uptime Monitoring Technician supports the 24/7 remote monitoring and basic management of EquipmentShare’s heavy equipment rental fleet and Customer Owned Equipment (COE). This role focuses on monitoring system alerts, assisting with incident triage, and escalating issues to senior team members to help maintain fleet uptime and performance. Primary Responsibilities Perform job duties in accordance with EquipmentShare’s vision, mission, and values. Monitor fleet systems and respond to events and alarms; assist with incident triage, documentation, and escalation in accordance with established processes. Support the incident management process by identifying potential issues, gathering relevant information, and escalating as needed. Collaborate with Services Technical Support and senior team members to assist in troubleshooting and resolving equipment issues. Coordinate with internal teams (e.g., Warranty, Service Technicians, Service Managers) to support issue resolution and ensure timely communication. Support other members of the Uptime Management Center and internal teams as needed to ensure effective operations and service delivery. Monitor service maintenance intervals. Monitor and respond to branch personnel/customer queries and requests across various communication channels such as chat, email, and phone. Follow-up with branch personnel and customers to ensure issues are resolved to their satisfaction before closing cases. Contribute to knowledge base documentation to support team learning and improve efficiency. Participate in training initiatives to support development toward a Fleet Monitoring Specialist role and enhance technical and operational knowledge. Work with dealerships on viewing and clearing critical alerts. Adhere to contractual SLO/SLA performance and support team KPIs. Represent the department professionally in interactions with internal teams and customers. Why EquipmentShare? Because we do things differently — and we think you’ll feel it from day one. We’re a people-first company powered by cutting-edge technology. That means our proprietary T3 platform doesn’t just run our business — it also makes your job easier, safer, and more connected. Whether you’re behind the wheel, under the hood, leading a branch, or closing deals — tech supports you, and you drive us forward. We’re a team of problem-solvers, go-getters, and builders. And we’re looking for teammates who take pride in doing meaningful work and want to be part of building something special. Perks & Benefits Competitive compensation Full medical, dental, and vision coverage for full-time employees Generous PTO + paid holidays 401(k) + company match Gym membership stipend + wellness programs (earn PTO and prizes!) Company events, food truck nights 16 hours of paid volunteer time per year — give back to the community you call home Career advancement, leadership training, and professional development opportunities About You You want to be part of a team that’s not just changing an industry for the sake of change — we’re transforming it to make it safer, more secure, and more productive. You bring grit, heart, and humility to your work, and you’re excited about the opportunity to grow within a fast-paced, mission-driven environment. We’re looking for people who: See challenges as opportunities Embrace change and continuous improvement Bring energy, effort, and optimism every day Skills & Qualifications A passion for helping others and a willingness to go the extra mile in providing nothing less than exceptional service and a positive customer experience. Basic understanding of heavy equipment, mechanical systems, or a demonstrated interest in developing technical expertise in this area. Must be able to work in a 7x24 environment with rotating shifts and a potential on-call schedule. Ability to maintain strict confidentiality. Strong organizational skills with attention to detail and accuracy. Strong time management and communication skills. Ability to leverage technology to improve communication and efficiency. Ability to multi-task and manage multiple priorities in a fast paced environment. Working knowledge of G-Suite, including Gmail, Google Docs, Sheets, and Drive. Ability to proofread and edit written content. Attention to detail with the ability to identify process gaps and escalate as appropriate. Ability to be flexible and adapt to change in a positive manner. Self-starter and highly motivated with a strong, positive work ethic that contributes to the vision of the department and the company as a whole. Must possess a professional yet enthusiastic and friendly demeanor. Education and Experience: Associate’s degree, technical certification, trade school training, or equivalent combination of education and experience preferred. 0-2 years of experience in customer support, operation, technical support, or a related field preferred Exposure to heavy equipment, mechanical systems, or fleet operations is a plus, but not required. Exposure or interest in coding, scripting, or SQL/database querying is preferred, but not required. Physical Requirements: Must be able to sit for prolonged periods at a desk and work on a computer. A Workplace For All At EquipmentShare, we believe the best solutions come from a team that reflects the world around us. Our initiative — A Workplace For All — is rooted in the belief that we must work together to solve some of the toughest problems in construction. That means attracting, developing, and retaining great people from all walks of life. We value different backgrounds, talents, and perspectives. We want you to feel like you belong here — because you do. EquipmentShare is an EOE M/F/D/ V. Employment is contingent on passing a background check. Additionally, some roles require passing a drug test, depending on the job responsibilities.", "summaryDescription" : "Fleet Monitoring Technician at EquipmentShare. Skills: Fleet monitoring, Incident management, Service delivery. Perform job duties. Monitor fleet systems", "postedDate" : "2026-06-14T07:59:41.879", "createdAt" : "2026-06-14T07:59:41.879", "lastUpdated" : "2026-06-15T09:29:26.714", "ingestTimestamp" : "2026-06-14T07:59:41.879", "mongoId" : "6a2c6b6874d8ee00a09121f2", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 45000, "salaryAnnualMax" : 65000, "salaryBand" : "30k-50k", "hasSalary" : true, "allSkills" : [ "Incident triage", "Issue escalation", "Troubleshooting equipment issues", "Service maintenance intervals", "Customer queries", "Customer requests", "Case resolution", "Knowledge base documentation", "Technical knowledge", "Operational knowledge", "Critical alerts", "SLO performance", "SLA performance", "Team KPIs", "Grit", "Heart", "Humility", "Energy", "Effort", "Optimism", "Fleet monitoring", "Incident management", "Service delivery", "Process management", "Cross-functional coordination", "Vendor management", "Stakeholder management", "Operational metrics", "Resource planning", "Continuous improvement", "Heavy equipment", "Mechanical systems", "Fleet operations", "Construction industry", "T3 platform" ], "skillCount" : 35, "jobCategory" : "operations", "jobSubcategory" : "general", "seniorityLevel" : "Junior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Logistics", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2a5d1174d8ee00a0617b63", "title" : "Program Manager, Business Practices", "company" : "Stripe", "industry" : "Financial Services", "salary" : { "min" : 1050000.0, "max" : 1650000.0, "currency" : "MXN", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Program Manager in the Technology industry in Mexico City, Mexico, adjusted for seniority and company size." }, "location" : "Mexico Locations", "locations" : [ "Mexico Locations" ], "timestamp" : "2026-06-14T22:00:43.590", "fingerprint" : "9df6c3a85457f89dbd55d90c1ecab43c9ee83bddee745eb7a99b7a3aa59de469", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://stripe.com/jobs/search?gh_jid=7942923", "externalId" : "7942923", "industryFunction" : { }, "structuredLocations" : [ { "country" : "Mexico", "continent" : "na", "workMode" : "onsite" } ], "locationText" : "Mexico", "experienceMinYears" : 7, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Excel, Google Sheet, Salesforce, CPQ, Deal Approval, Contract Lifecycle Management", "professionalSkills" : [ "Deal management", "Commercial transformation", "Business operations", "Management consulting", "Change management", "Stakeholder engagement", "Cross-functional team engagement", "Deal policy", "Process improvement", "Commercial activities", "Operational continuity", "Organizational knowledge", "Scalability", "Messaging planning", "Support planning", "Enablement planning", "Deal lifecycle improvement", "Strategy development", "Policy development", "Process development", "Technology development", "Data synthesis", "Strategy guidance", "Decision guidance", "Root cause analysis" ], "hardSkillsList" : [ "Deal management processes", "Commercial agreements", "Data analysis" ], "softSkillsList" : [ "Adaptability", "Flexibility", "Analytical", "Communication", "Influencing" ], "hardSkills" : [ { "name" : "Deal management processes", "level" : "intermediate" }, { "name" : "Commercial agreements", "level" : "intermediate" }, { "name" : "Data analysis", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Adaptability" }, { "name" : "Flexibility" }, { "name" : "Analytical" }, { "name" : "Communication" }, { "name" : "Influencing" } ], "majorSkills" : "Deal lifecycle, Commercial transformation, Business practices", "majorSkillsList" : [ "Deal lifecycle", "Commercial transformation", "Business practices" ], "coreResponsibilities" : "Solve GTM deal lifecycle challenges, Create scalable deal policies, Create efficient deal processes, Ensure seamless operational continuity, Establish documentation ecosystem, Maintain documentation ecosystem, Update documentation ecosystem, Manage change management activities, Coordinate change management activities, Develop collaborative relationships, Identify deal lifecycle improvement opportunities, Prioritize among projects, Synthesize data, Guide strategy, Support strategy, Guide decisions, Support decisions, Make exec recommendations, Drive exec decisions", "teamCollaboration" : "Cross-functional teams; Senior stakeholders; Sales teams; Cross-functional organizations", "projectManagementSkills" : [ "Program management", "Global programs", "Enterprise deal lifecycle programs", "Commercial transformation programs" ], "domainKnowledge" : "Financial infrastructure; GTM motion; Deal policy; Revenue contracting; Deal operations; Go-to-market; Commercial agreements; Payments; SaaS", "domainList" : [ "financial-infrastructure", "gtm-motion", "deal-policy", "revenue-contracting", "deal-operations", "go-to-market", "commercial-agreements", "payments", "saas" ], "domainSpecificKnowledge" : [ "Financial infrastructure", "GTM motion", "Deal policy", "Revenue contracting", "Deal operations", "Go-to-market", "Commercial agreements", "Payments", "SaaS" ], "toolProficiency" : [ "Salesforce", "CPQ", "Deal Approval", "Contract Lifecycle Management" ], "communicationSkills" : "Superior communication; Communication effectiveness; Presentation; Influencing across levels", "documentationSkills" : "Documentation ecosystem; Process maps; Strategic playbooks", "problemSolvingSkills" : "Diagnose problems; Simplify problems; Structure problems; Structure solutions; Problem solving; Analysis", "remoteFriendly" : false, "rawDescription" : "Who we are About Stripe Stripe is a financial infrastructure platform for businesses. Millions of companies—from the world’s largest enterprises to the most ambitious startups—use Stripe to accept payments, grow their revenue, and accelerate new business opportunities. Our mission is to increase the GDP of the internet, and we have a staggering amount of work ahead. That means you have an unprecedented opportunity to put the global economy within everyone’s reach while doing the most important work of your career. About the team Global Business Services’ (GBS) Business Practices team establishes and manages policies and processes for the GTM motion, including deal policy, approval and revenue contracting processes, and other deal related operations (e. g. misbilling, deal support models, etc). The team's reach is widespread across Stripe, not exclusive to one sales segment or geographical region; GBS drives change across go-to-market, positively impacting Stripe users, and cross-functional teams. GBS’s priorities are set through the direction of Stripe leadership and executive vision, partnership with sales and cross-functional organizations. This role sits within Global Business Practices’ Business Practices team, responsible for establishing, managing, and improving policies and processes to improve deal quality and velocity for Stripe. What you’ll do Our Business Practices Program Managers are focused on solving GTM’s deal lifecycle challenges to create scalable and efficient deal policies and processes in support of commercial activities. We are looking for a self-starter who has demonstrated success dealing with ambiguous global-scale programs, with multi-layered stakeholder management and significant cross-functional team engagement. The ideal candidate will: (1) have deal policy and process background working at a hypergrowth technology/GTM org, (2) have superior communication skills to work across senior stakeholders across different functions, and (3) thrive when solving complex problems with limited oversight ensure seamless operational continuity through rigorous performance standards, cultural alignment, and optimized hand-off protocols. Establish and maintain a gold-standard documentation ecosystem, ensuring all program methodologies, process maps, and strategic playbooks are accurate, accessible, and continuously updated to support organizational knowledge and scalability. Manage directly (or coordinate) the ‘full-stack’ of change management activities across stakeholder engagement and creating champions, messaging/communication planning, support and enablement Develop strong collaborative relationships with key stakeholders across Stripe across levels and functions Work cross-functionally to proactively identify deal lifecycle improvement opportunities for the GTM teams spanning strategy, people, policy, process, and/or technology Seamlessly prioritize among various projects and synthesize data to guide/support strategy and decision Make exec level recommendations and drive decisions, where necessary Who you are We're looking for someone who meets the minimum requirements to be considered for the role. If you meet these requirements, you are encouraged to apply. The preferred qualifications are a bonus, not a requirement. Minimum requirements A strong track record of delivering global, complex enterprise deal lifecycle/commercial transformation programs with multiple constituents in a changing, ambiguous environment end-to-end Experience with deal management processes, deal process related root cause analysis, and commercial agreements 7+ years of experience in program management, business operations, management consulting or a related discipline Works well under pressure, with a high degree of adaptability and flexibility in a fast paced, rapidly changing environment The ability to diagnose, simplify and structure problems and solutions while having command of “the details” Enthusiastic “roll up your sleeves” mentality Excellent analytical, presentation, and communication experience, influencing across all levels from front lines to executive stakeholders. You set a high-bar in terms of communication effectiveness. Comfort with Excel and/or Google Sheet for analyzing large datasets Prior experience with Salesforce, CPQ, Deal Approval, Contract Lifecycle Management tools Preferred qualifications Comfort operating with incomplete data and adapting / re-prioritizing activities as business needs change Deep problem solving and analysis experience (solving business problems - commercial, operational, financial) in a sales-oriented environment A growth mindset and innate curiosity where every interaction is an opportunity to learn and improve (yourself, and those around you) You demonstrate leadership qualities throughout your work – taking ownership of challenges, selflessly supporting your colleagues, and setting the standard for quality in your deliverables Prior experience with payments and/or SaaS", "summaryDescription" : "Program Manager, Business Practices at Stripe. Skills: Deal lifecycle, Commercial transformation, Business practices. Solve GTM deal lifecycle challenges. Create scalable deal policies", "postedDate" : "2026-06-11T18:16:47.308", "createdAt" : "2026-06-11T18:16:47.308", "lastUpdated" : "2026-06-14T22:00:43.590", "ingestTimestamp" : "2026-06-11T18:16:47.308", "mongoId" : "6a2a5d1174d8ee00a0617b63", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ "Deal management processes", "Commercial agreements", "Data analysis", "Adaptability", "Flexibility", "Analytical", "Communication", "Influencing", "Deal lifecycle", "Commercial transformation", "Business practices", "Deal management", "Business operations", "Management consulting", "Change management", "Stakeholder engagement", "Cross-functional team engagement", "Deal policy", "Process improvement", "Commercial activities", "Operational continuity", "Organizational knowledge", "Scalability", "Messaging planning", "Support planning", "Enablement planning", "Deal lifecycle improvement", "Strategy development", "Policy development", "Process development", "Technology development", "Data synthesis", "Strategy guidance", "Decision guidance", "Root cause analysis", "Program management", "Global programs", "Enterprise deal lifecycle programs", "Commercial transformation programs", "Financial infrastructure", "GTM motion", "Revenue contracting", "Deal operations", "Go-to-market", "Payments", "SaaS", "Salesforce", "CPQ", "Deal Approval", "Contract Lifecycle Management" ], "skillCount" : 50, "jobCategory" : "operations", "jobSubcategory" : "1510-gtm-business-operations", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Financial Services" }, { "id" : "6a2c6bdb74d8ee00a0915692", "title" : "HVAC Monitoring Technician", "company" : "Kelso Building Services", "salary" : { "min" : 42000.0, "max" : 58000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "The estimation is based on the market baseline for an Entry-level HVAC Monitoring Technician in Draper, United States, with adjustments for company size and industry." }, "location" : "Draper, Utah, United States", "locations" : [ "Draper", "Utah", "United States" ], "certifications" : [ "Certification programs for monitoring center operations" ], "timestamp" : "2026-06-16T06:01:36.905", "fingerprint" : "8d579a2eebb20b9501e543397e6eb870ffe9fe8a63731a9528e0707567544e8d", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://kelsobuildingservices.com/careers/?gh_jid=5238958008", "externalId" : "5238958008", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Draper", "state" : "Utah", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "40.5247777,-111.8627989" } ], "locationText" : "Draper, Utah, United States", "technicalSkills" : "Building automation systems, HVAC controls", "professionalSkills" : [ "Situational awareness", "Prioritization", "Process adherence", "Judgment", "Teamwork" ], "hardSkillsList" : [ "Remote support", "Alarm review", "System monitoring", "Troubleshooting" ], "hardSkills" : [ { "name" : "Remote support", "level" : "intermediate" }, { "name" : "Alarm review", "level" : "intermediate" }, { "name" : "System monitoring", "level" : "intermediate" }, { "name" : "Troubleshooting", "level" : "intermediate" } ], "majorSkills" : "System monitoring, Alarm response, Customer communication, Service coordination", "majorSkillsList" : [ "System monitoring", "Alarm response", "Customer communication", "Service coordination" ], "coreResponsibilities" : "Monitor building automation systems, Monitor HVAC systems, Monitor electrical systems, Monitor related systems, Respond to alerts, Review alarms, Prioritize alarms, Distinguish critical alerts, Distinguish informational notifications, Initiate escalation actions, Act as primary contact, Deliver clear communication, Deliver professional communication, Record interactions accurately, Collaborate with technicians, Collaborate with internal teams, Access customer systems securely, Analyze alarms, Analyze trends, Analyze system data, Perform remote actions, Document findings, Document outcomes, Create service tickets, Manage service tickets, Coordinate technician dispatch, Monitor service progress, Provide updates to stakeholders, Maintain records, Generate reports, Ensure compliance", "teamCollaboration" : "Internal service teams; Technicians; Stakeholders", "domainKnowledge" : "Building systems; Customer processes; Security practices; Monitoring center operations; Mechanical systems; Electrical systems", "domainList" : [ "building-systems", "customer-processes", "security-practices", "monitoring-center-operations", "mechanical-systems", "electrical-systems" ], "domainSpecificKnowledge" : [ "Building systems", "Customer processes", "Security practices", "Monitoring center operations", "Mechanical systems", "Electrical systems" ], "toolProficiency" : [ "Remote tools", "Ticketing platforms", "Service management platforms" ], "communicationSkills" : "Professional communication; Clear communication", "documentationSkills" : "Accurate documentation; Standardized service records", "continuousLearning" : "Ongoing learning; Quality improvement initiatives; Required training; Certification programs; Structured training pathways", "problemSolvingSkills" : "Issue identification; Troubleshooting; Decision-making", "specialRequirements" : "Rotating shifts, Evenings, Weekends, Holidays", "outcomesObjectives" : "Timely response to alerts; Accuracy in evaluation; Accuracy in escalation; Quality documentation; Completeness of documentation; Meeting service level agreements; Positive customer feedback; Completion of training; Completion of certifications", "qualificationsBasic" : "High school diploma or equivalent, Computer skills, Excellent written communication skills, Excellent verbal communication skills, Ability to follow structured procedures, Ability to follow escalation processes, High level of accuracy, Attention to detail, Ability to stay composed in time-sensitive situations, Flexibility to work rotating schedules, Flexibility to work nights, Flexibility to work weekends", "qualificationsPreferred" : "Technical education is a plus, Experience with building automation systems, Experience with HVAC controls, Experience with facilities operations, Background in monitoring centers, Background in help desks, Background in dispatch, Background in call centers, Familiarity with ticketing platforms, Familiarity with service management platforms", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "At Kelso Building Services (KBS), we invest in our people by providing the training, tools, and support needed to succeed. Our culture is built on accountability, innovation, and delivering an exceptional customer experience. Team members have the opportunity to grow within a forward-thinking organization supporting critical building operations nationwide. We are hiring both Level 1 and Level 2 Operators, based on experience. Rotating shifts that may include evenings, weekends, and holidays. Role Summary This person serves as a key point of contact for KBS’s 24/7 monitoring services. This position is responsible for overseeing customer building systems in real time, responding to alerts, and coordinating service actions using established procedures. This is a structured, fast-moving role that requires strong attention to detail and adherence to processes. Operators act as the bridge between customer facilities and internal service teams. Level 1 Operators focus on alarm review, communication, documentation, and basic remote support tasks. Level 2 Operators bring additional technical experience and handle more advanced troubleshooting and decision-making. Core Responsibilities System Monitoring & Response Continuously monitor building automation, HVAC, electrical, and related systems for alerts or irregular activity Review and prioritize alarms using predefined workflows and response criteria Distinguish between critical alerts and informational notifications using established guidelines Initiate appropriate escalation actions based on customer-specific protocols Customer Communication & Support Act as a primary contact for customer emails and phone inquiries Deliver clear, professional communication during service events Record all interactions accurately within internal systems Collaborate with technicians and internal teams to ensure timely resolutions Remote Troubleshooting Access customer systems securely using approved remote tools Analyze alarms, trends, and system data to support issue identification Perform approved remote actions such as resets, schedule checks, and setpoint verification Document findings and outcomes in standardized service records Dispatch & Service Coordination Create and manage service tickets within company platforms Coordinate technician dispatch based on scope, urgency, and approval requirements Monitor service progress and provide updates to stakeholders Reporting & Documentation Maintain complete and audit-ready records of all activities Generate reports related to alarms, system performance, and service activity Ensure compliance with service standards and response expectations Training & Development Complete required training in building systems, customer processes, and security practices Participate in certification programs for monitoring center operations Engage in ongoing learning and quality improvement initiatives Basic Qualifications Required: High school diploma or equivalent (technical education is a plus) Strong computer skills with the ability to navigate multiple systems simultaneously Excellent written and verbal communication skills Ability to follow structured procedures and escalation processes High level of accuracy and attention to detail Ability to stay composed in time-sensitive situations Flexibility to work rotating schedules, including nights and weekends Preferred (Level 2): Experience with building automation systems (BAS), HVAC controls, or facilities operations Background in monitoring centers, help desks, dispatch, or call centers Familiarity with ticketing or service management platforms Basic knowledge of mechanical or electrical systems Key Skills & Attributes Strong situational awareness and prioritization ability Consistency in following defined processes Customer-first mindset Sound judgment when escalating issues Effective teamwork and communication Commitment to learning and professional growth Performance Expectations Success in this role is measured by: Timely response to system alerts Accuracy in issue evaluation and escalation Quality and completeness of documentation Meeting service level agreements (SLAs) Positive customer feedback Completion of required training and certifications Growth Opportunities This role provides a starting point for long-term careers within KBS’s operations and technology teams. Advancement opportunities may include: ROC Operator – Level 2 Remote Systems Specialist Building Automation Support Operations Supervisor Monitoring & Analytics roles Advancement is performance-based and supported by structured training pathways. Why Work at KBS Be part of a growing digital facilities and remote operations platform Gain exposure to advanced smart building technologies Access formal training and certification programs Contribute to mission-critical operations that impact customer uptime Join a company focused on safety, performance, and innovation Compensation & Benefits Competitive hourly pay Medical benefits package Paid time off 401(k) with company match", "summaryDescription" : "HVAC Monitoring Technician at Kelso Building Services. Skills: System monitoring, Alarm response, Customer communication, Service coordination. Monitor building automation systems. Monitor HVAC systems", "postedDate" : "2026-06-14T20:07:58.305", "createdAt" : "2026-06-14T20:07:58.305", "lastUpdated" : "2026-06-16T06:01:36.905", "ingestTimestamp" : "2026-06-14T20:07:58.305", "mongoId" : "6a2c6bdb74d8ee00a0915692", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 42000, "salaryAnnualMax" : 58000, "salaryBand" : "30k-50k", "hasSalary" : true, "allSkills" : [ "Remote support", "Alarm review", "System monitoring", "Troubleshooting", "Alarm response", "Customer communication", "Service coordination", "Situational awareness", "Prioritization", "Process adherence", "Judgment", "Teamwork", "Building systems", "Customer processes", "Security practices", "Monitoring center operations", "Mechanical systems", "Electrical systems", "Certification programs for monitoring center operations", "Remote tools", "Ticketing platforms", "Service management platforms" ], "skillCount" : 22, "jobCategory" : "operations", "jobSubcategory" : "general", "seniorityLevel" : "Entry", "dataQualityScore" : 0.7777778, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Real Estate", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2c5f3f74d8ee00a08ea545", "title" : "Observability Platform Engineer", "company" : "Nscale", "industry" : "Technology", "salary" : { "min" : 75000.0, "max" : 105000.0, "currency" : "GBP", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for a Mid-level Observability Platform Engineer in the UK Technology industry, adjusted for London's high cost of living." }, "location" : "UK", "locations" : [ "UK" ], "timestamp" : "2026-06-14T23:55:12.488", "fingerprint" : "f47f5759818468ae9ad6bc7cea5a412348570f01063d7384d78585fe6b673f7c", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.eu.greenhouse.io/nscaleoperationsukltd/jobs/4896731101", "externalId" : "4896731101", "industryFunction" : { }, "structuredLocations" : [ { "country" : "United Kingdom", "continent" : "eu", "workMode" : "onsite" } ], "locationText" : "United Kingdom", "technicalSkills" : "Prometheus, Grafana, Datadog, ELK, Opensearch, Splunk, OpenTelemetry, Jaeger, Kubernetes, Containers, Service meshes, Python, Go, Bash, Terraform, Ansible, Pulumi", "professionalSkills" : [ "System design", "Performance tuning", "Incident management", "Telemetry analytics" ], "hardSkillsList" : [ "Observability platforms", "Monitoring", "Logging", "Tracing", "Alerting", "Infrastructure-as-Code", "CI/CD pipelines", "Telemetry instrumentation", "Performance diagnosis" ], "softSkillsList" : [ "Ownership", "Accountability", "Openness", "Transparency" ], "hardSkills" : [ { "name" : "Observability platforms", "level" : "intermediate" }, { "name" : "Monitoring", "level" : "intermediate" }, { "name" : "Logging", "level" : "intermediate" }, { "name" : "Tracing", "level" : "intermediate" }, { "name" : "Alerting", "level" : "intermediate" }, { "name" : "Infrastructure-as-Code", "level" : "intermediate" }, { "name" : "CI/CD pipelines", "level" : "intermediate" }, { "name" : "Telemetry instrumentation", "level" : "intermediate" }, { "name" : "Performance diagnosis", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Ownership" }, { "name" : "Accountability" }, { "name" : "Openness" }, { "name" : "Transparency" } ], "majorSkills" : "Observability platforms, Monitoring, Logging, Tracing", "majorSkillsList" : [ "Observability platforms", "Monitoring", "Logging", "Tracing" ], "coreResponsibilities" : "Design observability platforms, Build observability platforms, Maintain observability platforms, Deploy observability tools, Manage observability tools, Automate observability infrastructure, Instrument applications for telemetry, Instrument systems for telemetry, Develop dashboards, Develop alerts, Develop analytics, Ensure data accuracy, Ensure data reliability, Ensure data retention, Troubleshoot platform issues, Drive adoption of best practices, Contribute to incident detection, Contribute to incident response, Contribute to incident resolution, Document observability standards, Document observability tools, Document observability processes", "teamCollaboration" : "Work with SRE teams; Work with Infrastructure teams; Work with Engineering teams; Partner with engineering teams; Partner with SRE teams; Work with product teams", "projectManagementSkills" : [ "CI/CD practices" ], "domainKnowledge" : "AI datacenter infrastructure; GPU cloud infrastructure; Distributed systems reliability; Cloud-native infrastructure; AIOps; Hyperscale datacenter environments; Sustainability monitoring", "domainList" : [ "ai-datacenter-infrastructure", "gpu-cloud-infrastructure", "distributed-systems-reliability", "cloud-native-infrastructure", "aiops", "hyperscale-datacenter-environments", "sustainability-monitoring" ], "domainSpecificKnowledge" : [ "AI datacenter infrastructure", "GPU cloud infrastructure", "Distributed systems reliability", "Cloud-native infrastructure", "AIOps", "Hyperscale datacenter environments", "Sustainability monitoring" ], "toolProficiency" : [ "Prometheus", "Grafana", "Datadog", "ELK", "Opensearch", "Splunk", "OpenTelemetry", "Jaeger", "Terraform", "Ansible", "Pulumi" ], "documentationSkills" : "Document observability standards; Document observability tools; Document observability processes", "innovationCreativity" : "Relentless innovation", "problemSolvingSkills" : "Problem-solving; Diagnose performance issues", "qualificationsBasic" : "Experience in designing observability platforms, Experience operating observability platforms at scale, Hands-on expertise with monitoring tools, Hands-on expertise with logging tools, Hands-on expertise with tracing tools, Experience with cloud-native infrastructure, Proficiency in scripting/automation, Knowledge of Infrastructure-as-Code, Knowledge of CI/CD practices, Understanding of distributed systems reliability, Understanding of incident management, Excellent problem-solving skills, Ability to diagnose performance issues", "qualificationsPreferred" : "Experience with AI/ML workload observability, Familiarity with hyperscale datacenter environments, Knowledge of AIOps, Knowledge of advanced telemetry analytics, Exposure to sustainability monitoring", "rawDescription" : "About Nscale Nscale is the GPU cloud engineered for AI. We provide cost-effective, high-performance infrastructure for AI start-ups and large enterprise customers. Nscale enables AI-focused companies to achieve superior results by reducing the complexity of AI development. Our GPU cloud bolsters technical capabilities and directly supports strategic business outcomes, including cost management, rapid innovation, and environmental responsibility. We thrive on a culture of relentless innovation, ownership, and accountability, where every team member takes pride in their work and drives it with excellence and urgency. As an Nscaler, you’ll build trust through openness and transparency, where everyone is inspired to do their best work. If you join our team, you’ll be contributing to building the technology that powers the future. About The Role Nscale is seeking an Observability Platform Engineer to design, deploy, and operate the monitoring, logging, and tracing systems that power observability across our global AI datacenter infrastructure. You will focus on scalability, automation, and integration of observability platforms, ensuring that metrics, logs, and traces are accurate, accessible, and actionable. You’ll work closely with SRE, Infrastructure, and Engineering teams to ensure our GPU-powered cloud is fully instrumented for reliability and performance. What You'll Be Doing Design, build, and maintain observability platforms (monitoring, logging, tracing, alerting) at global scale. Deploy and manage tools such as Prometheus, Grafana, Datadog, ELK/Opensearch, OpenTelemetry, and Jaeger. Automate observability infrastructure using Infrastructure-as-Code and CI/CD pipelines. Partner with engineering and SRE teams to instrument applications and systems for telemetry. Develop dashboards, alerts, and analytics to provide real-time visibility into infrastructure health. Ensure observability data is accurate, reliable, and retained per compliance requirements. Troubleshoot observability platform issues, ensuring high availability and performance. Drive adoption of best practices for monitoring, logging, and tracing across the company. Contribute to continuous improvement of incident detection, response, and resolution. Document observability standards, tools, and processes. About You (Skills / Qualifications) Strong experience in designing and operating observability platforms at scale. Hands-on expertise with monitoring, logging, and tracing tools (Prometheus, Grafana, Datadog, ELK/Opensearch, Splunk, OpenTelemetry, Jaeger). Experience with cloud-native infrastructure (Kubernetes, containers, service meshes). Proficiency in scripting/automation (e.g., Python, Go, Bash). Knowledge of Infrastructure-as-Code (Terraform, Ansible, Pulumi) and CI/CD practices. Strong understanding of distributed systems reliability and incident management. Excellent problem-solving skills with the ability to diagnose performance issues across systems. Good collaboration skills to work with engineering, operations, and product teams. Nice to have: Experience with AI/ML workload observability. Familiarity with hyperscale datacenter environments. Knowledge of AIOps and advanced telemetry analytics. Exposure to sustainability monitoring (e.g., power usage effectiveness, efficiency metrics). Equal Opportunities Statement At Nscale, we are committed to fostering an inclusive, diverse, and equitable workplace. We believe that a variety of perspectives enriches our work environment, and we encourage applications from candidates of all backgrounds, experiences, and abilities. We strongly encourage applications from people of colour, the LGBTQ+ community, people with disabilities, neurodivergent people, parents, carers, and people from lower socio-economic backgrounds. If there’s anything we can do to accommodate your specific situation, please let us know. For information on how Nscale handles candidate personal data, please see our Employee & Candidate Privacy Notice: Here.", "summaryDescription" : "Observability Platform Engineer at Nscale. Skills: Observability platforms, Monitoring, Logging, Tracing. Design observability platforms. Build observability platforms", "postedDate" : "2026-06-12T22:13:51.237", "createdAt" : "2026-06-12T22:13:51.237", "lastUpdated" : "2026-06-14T23:55:12.488", "ingestTimestamp" : "2026-06-12T22:13:51.237", "mongoId" : "6a2c5f3f74d8ee00a08ea545", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "75k-100k", "hasSalary" : false, "allSkills" : [ "Observability platforms", "Monitoring", "Logging", "Tracing", "Alerting", "Infrastructure-as-Code", "CI/CD pipelines", "Telemetry instrumentation", "Performance diagnosis", "Ownership", "Accountability", "Openness", "Transparency", "System design", "Performance tuning", "Incident management", "Telemetry analytics", "CI/CD practices", "AI datacenter infrastructure", "GPU cloud infrastructure", "Distributed systems reliability", "Cloud-native infrastructure", "AIOps", "Hyperscale datacenter environments", "Sustainability monitoring", "Prometheus", "Grafana", "Datadog", "ELK", "Opensearch", "Splunk", "OpenTelemetry", "Jaeger", "Terraform", "Ansible", "Pulumi" ], "skillCount" : 36, "jobCategory" : "operations", "jobSubcategory" : "ai-infrastructure-operations", "dataQualityScore" : 0.7777778, "daysOld" : 2, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology" }, { "id" : "6a2c92ed74d8ee00a0986e2a", "title" : "Monitoring / AIOps Engineer", "company" : "Xebia", "industry" : "Technology", "salary" : { "min" : 140000.0, "max" : 200000.0, "currency" : "PLN", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Mid-level AIOps Engineer in Poland, adjusted for the technology industry and a mid-sized company." }, "location" : "Poland", "locations" : [ "Poland" ], "timestamp" : "2026-06-15T08:01:01.537", "fingerprint" : "e62914972c0e981e8287dadc26c8b19babdde48a7eee663b2517df78dc12f712", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.greenhouse.io/xebiacee/jobs/5996092004", "externalId" : "5996092004", "industryFunction" : { }, "structuredLocations" : [ { "country" : "Poland", "continent" : "eu", "workMode" : "onsite" } ], "locationText" : "Poland", "experienceMinYears" : 3, "experienceMaxYears" : 5, "experienceLevel" : "Mid", "technicalSkills" : "Datadog, Splunk, AppDynamics, Prometheus, Grafana, ELK, OpenTelemetry, Python, Bash, AWS, Azure, GCP, Jaeger, Zipkin", "professionalSkills" : [ "Observability engineering", "AIOps engineering", "Capacity planning", "Performance trending" ], "hardSkillsList" : [ "Log aggregation", "Metric collection", "Distributed tracing", "Alerting rules tuning", "SLO-based dashboards", "Service health reporting", "Anomaly detection agents" ], "hardSkills" : [ { "name" : "Log aggregation", "level" : "intermediate" }, { "name" : "Metric collection", "level" : "intermediate" }, { "name" : "Distributed tracing", "level" : "intermediate" }, { "name" : "Alerting rules tuning", "level" : "intermediate" }, { "name" : "SLO-based dashboards", "level" : "intermediate" }, { "name" : "Service health reporting", "level" : "intermediate" }, { "name" : "Anomaly detection agents", "level" : "intermediate" } ], "majorSkills" : "Monitoring, AIOps, Observability, Cloud-native monitoring", "majorSkillsList" : [ "Monitoring", "AIOps", "Observability", "Cloud-native monitoring" ], "coreResponsibilities" : "Maintain monitoring configurations, Improve monitoring configurations, Build alerting rules, Tune alerting rules, Create SLO-based dashboards, Maintain SLO-based dashboards, Create service health reporting, Maintain service health reporting, Implement log aggregation, Implement metric collection, Implement distributed tracing, Support AI agents deployment, Support AI agents tuning, Collaborate with SRE teams, Automate monitoring onboarding, Provide CET-timezone coverage, Participate in capacity planning, Participate in performance trending, Document monitoring standards, Contribute to knowledge base", "teamCollaboration" : "SRE Engineering teams; European delivery model", "domainKnowledge" : "SLI/SLO/SLA frameworks; AI-powered correlation; Anomaly detection; Monitoring-as-code; Large-scale environments; Multi-cloud environments", "domainList" : [ "sli-slo-sla-frameworks", "ai-powered-correlation", "anomaly-detection", "monitoring-as-code", "large-scale-environments", "multi-cloud-environments" ], "domainSpecificKnowledge" : [ "SLI/SLO/SLA frameworks", "AI-powered correlation", "Anomaly detection", "Monitoring-as-code", "Large-scale environments", "Multi-cloud environments" ], "toolProficiency" : [ "Datadog", "Splunk", "AppDynamics", "Prometheus", "Grafana", "ELK", "OpenTelemetry", "Jaeger", "Zipkin", "Terraform", "Ansible", "Claude Code", "GitHub Copilot", "Cursor" ], "communicationSkills" : "English communication", "documentationSkills" : "Documenting standards; Internal knowledge base", "continuousLearning" : "Personal development budgets; Guilds; Labs", "innovationCreativity" : "Emerging AI-driven practices; Agent-based workflows; AI-augmented development", "problemSolvingSkills" : "Reduce noise; Improve signal quality; Root cause analysis", "specialRequirements" : "Work from EU region, Work permit required", "qualificationsBasic" : "3-5 years experience, Practical AI assistant experience, Hands-on Datadog experience, Hands-on Splunk experience, Hands-on AppDynamics experience, Experience with metrics pipelines, Experience with logs pipelines, Experience with tracing pipelines, Proficiency in Python, Proficiency in Bash, Experience with AWS monitoring, Experience with Azure monitoring, Experience with GCP monitoring, Knowledge of alert correlation, Knowledge of noise reduction, Good English communication", "qualificationsPreferred" : "Experience applying GenAI, Interest in AI-driven practices, Experience with AIOps platforms, Experience with ML anomaly detection, Familiarity with monitoring-as-code, Knowledge of distributed tracing tools, Experience in multi-cloud environments", "remoteFriendly" : true, "rawDescription" : "Who We Are While Xebia is a global tech company, our journey in CEE started with two Polish companies – PGS Software, known for world-class cloud and software solutions, and GetInData, a pioneer in Big Data. Today, we’re a team of 1,000+ experts delivering top-notch work across cloud, data, and software. And we’re just getting started. What We Do We work on projects that matter – and that make a difference. From fintech and e-commerce to aviation, logistics, media, and fashion, we help our clients build scalable platforms, data and AI solutions, and cutting-edge applications to shape the future of tech. Our clients include McLaren, Aviva, Deloitte, Spotify, Disney, ING, UPS, Tesco, Truecaller, AllSaints, Volotea, Schmitz Cargobull, Allegro, InPost, and many, many more. We value smart tech, real ownership, and continuous growth. We use modern, open-source stacks, and we’re proud to be trusted partners of Databricks, dbt, Snowflake, Azure, GCP, and AWS. Fun fact: we were the first AWS Premier Partner in Poland! Beyond Projects What makes Xebia special? Our community. We support tech communities, organize meetups (Software Talks, Data Tech Talks), and have a culture that actively support your growth via Guilds, Labs, and personal development budgets — for both tech and soft skills. It’s not just a job. It’s a place to grow. What sets us apart? Our mindset. Our vibe. Our people. And while that’s hard to capture in text – come visit us and see for yourself. You will be: maintaining and improving monitoring configurations across Datadog, Splunk, and AppDynamics, building and tuning alerting rules to reduce noise and improve signal quality, creating and maintaining SLO-based dashboards and service health reporting, implementing log aggregation, metric collection, and distributed tracing pipelines, supporting deployment and tuning of AI-powered correlation and anomaly detection agents, collaborating with SRE Engineering teams on observability maturity progression initiatives, automating monitoring onboarding for new applications, providing CET-timezone monitoring engineering coverage as part of the European delivery model, participating in capacity planning and performance trending analysis, documenting monitoring standards and contributing to the internal knowledge base. Your profile: 3–5 years of experience in monitoring, observability, or AIOps engineering, practical experience using AI-powered assistants (e.g. Claude Code, GitHub Copilot, Cursor) to improve productivity, quality, or decision-making in software delivery, hands-on experience with Datadog, Splunk, or similar observability platforms, experience working with metrics, logs, and tracing pipelines using tools such as Prometheus, Grafana, ELK, or OpenTelemetry, understanding of SLI/SLO/SLA frameworks, proficiency in scripting languages such as Python or Bash for automation, experience with cloud-native monitoring in AWS, Azure, or GCP environments, knowledge of alert correlation and noise reduction techniques, good English communication skill (at least B2 level). Work from the European Union region and a work permit are required. Nice to have: experience applying GenAI in a more structured way within the SDLC, including defined workflows, prompt patterns, or tool integrations embedded into daily work, interest in and familiarity with emerging AI-driven practices (e.g., agent-based workflows, automation patterns, AI- augmented development), with a willingness to explore and experiment beyond standard approaches, experience with AIOps platforms or ML-based anomaly detection, familiarity with monitoring-as-code approaches using Terraform or Ansible, knowledge of distributed tracing tools such as Jaeger, Zipkin, or OpenTelemetry, experience in large-scale, multi-cloud environments. Recruitment Process: CV review – HR call – Technical Interview – Client Interview – Decision", "summaryDescription" : "Monitoring / AIOps Engineer at Xebia. Skills: Monitoring, AIOps, Observability, Cloud-native monitoring. Maintain monitoring configurations. Improve monitoring configurations", "postedDate" : "2026-06-13T22:39:24.077", "createdAt" : "2026-06-13T22:39:24.077", "lastUpdated" : "2026-06-15T08:01:01.537", "ingestTimestamp" : "2026-06-13T22:39:24.077", "mongoId" : "6a2c92ed74d8ee00a0986e2a", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "100k-150k", "hasSalary" : false, "allSkills" : [ "Log aggregation", "Metric collection", "Distributed tracing", "Alerting rules tuning", "SLO-based dashboards", "Service health reporting", "Anomaly detection agents", "Monitoring", "AIOps", "Observability", "Cloud-native monitoring", "Observability engineering", "AIOps engineering", "Capacity planning", "Performance trending", "SLI/SLO/SLA frameworks", "AI-powered correlation", "Anomaly detection", "Monitoring-as-code", "Large-scale environments", "Multi-cloud environments", "Datadog", "Splunk", "AppDynamics", "Prometheus", "Grafana", "ELK", "OpenTelemetry", "Jaeger", "Zipkin", "Terraform", "Ansible", "Claude Code", "GitHub Copilot", "Cursor" ], "skillCount" : 35, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Mid", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a30556ef292fd229cf1f7f4", "title" : "Junior Observability Engineer", "company" : "Miratech", "industry" : "Information Technology And Services", "salary" : { "min" : 600000.0, "max" : 900000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Junior Observability Engineer in Jaipur, India, adjusted for entry-level experience and full-time employment in the technology sector." }, "location" : "Jaipur, IN", "locations" : [ "Jaipur", "IN" ], "timestamp" : "2026-06-16T08:16:13.246", "fingerprint" : "19c5c6a13371a619c6147f746c952c27192f85836d37181271f4a6eeb6eed8b1", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Miratech1/744000131875699-site-reliability-engineer-with-splunk", "externalId" : "744000131875699", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Jaipur", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "26.9154576,75.8189817" } ], "locationText" : "Jaipur, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "mid", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Miratech helps visionaries change the world. We are a global IT services and consulting company that brings together enterprise and start-up innovation. Today, we support digital transformation for some of the world's largest enterprises. By partnering with both large and small players, we stay at the leading edge of technology, remain nimble even as a global leader, and create technology that helps our clients further enhance their business. We are a valuesdriven organization and our culture of Relentless Performance has enabled over 99% of Miratech's engagements to succeed by meeting or exceeding our scope, schedule, and/or budget objectives since our inception in 1989. Miratech has coverage across 5 continents and operates in 25 countries around the world. Miratech retains nearly 1000 full-time professionals, and our annual growth rate exceeds 25%. We are looking for a Junior Observability Engineer to design, implement, and optimize enterprise observability solutions across applications, infrastructure, and cloud environments. This role focuses on monitoring, telemetry, automation, reliability engineering, and AIOps capabilities to improve system visibility, operational efficiency, and service reliability. The ideal candidate will have hands-on experience with observability platforms, cloud technologies, automation, and incident management practices while collaborating with engineering and operations teams to establish observability standards and best practices. Responsibilities * Design and implement end-to-end observability solutions across applications, infrastructure, and cloud environments. * Develop dashboards, alerts, and telemetry frameworks to provide real-time visibility into system health and performance. * Build automation solutions to eliminate repetitive operational tasks and improve efficiency. * Enable runbook automation, self-healing capabilities, and automated incident triage workflows. * Define and implement SLIs, SLOs, and alerting strategies to improve service reliability. * Drive improvements in MTTD and MTTR through actionable alerts and telemetry-driven insights. * Implement proactive monitoring, anomaly detection, and predictive alerting to identify issues before customer impact. * Leverage AIOps capabilities for alert correlation and intelligent incident response. * Integrate observability platforms with CI/CD pipelines, cloud services, and ITSM tools such as ServiceNow. * Collaborate with engineering, product, and operations teams to establish observability standards and operational readiness practices. ## Qualifications * 3+ years of experience in Observability Engineering, Site Reliability Engineering, or related domains. * Hands-on experience with observability platforms such as Splunk, Dynatrace, Grafana, and OpenTelemetry. * Strong expertise in AWS and GCP knowledge, with familiarity with cloud-native architectures. * Proficiency in Python for automation and operational tooling. * Experience implementing metrics, logs, events, and distributed tracing (MELT) across distributed systems. * Hands-on experience with Terraform and Infrastructure as Code practices. * Strong understanding of SLIs, SLOs, alerting strategies, and incident response frameworks. * Excellent troubleshooting, communication, and collaboration skills. * Bachelor's degree in Computer Science, Information Technology, or a related field (or equivalent experience). Nice to Have * Experience with AIOps platforms and intelligent alerting solutions. * Knowledge of Kubernetes and containerized environments. * Experience integrating observability tools with ServiceNow and CI/CD ecosystems. * AWS, GCP, Observability, or SRE-related certifications. We offer: * Culture of Relentless Performance : join an unstoppable technology development team with a 99% project success rate and more than 30% year-over-year revenue growth. * Competitive Pay and Benefits : enjoy a comprehensive compensation and benefits package, including health insurance, language courses, and a relocation program. * Work From Anywhere Culture : make the most of the flexibility that comes with remote work. * Growth Mindset : reap the benefits of a range of professional development opportunities, including certification programs, mentorship and talent investment programs, internal mobility and internship opportunities. * Global Impact : collaborate on impactful projects for top global clients and shape the future of industries. * Welcoming Multicultural Environment : be a part of a dynamic, global team and thrive in an inclusive and supportive work environment with open communication and regular team-building company social events. * Social Sustainability Values : join our sustainable business practices focused on five pillars, including IT education, community empowerment, fair operating practices, environmental sustainability, and gender equality. Miratech is an equal opportunity employer and does not discriminate against any employee or applicant for employment on the basis of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or any other protected status under applicable law. ## Additional Information All your information will be kept confidential according to EEO guidelines.", "summaryDescription" : "Junior Observability Engineer at Miratech", "postedDate" : "2026-06-12T11:16:45.000", "createdAt" : "2026-06-15T23:40:43.436", "lastUpdated" : "2026-06-16T08:16:13.246", "ingestTimestamp" : "2026-06-15T23:40:43.436", "mongoId" : "6a30556ef292fd229cf1f7f4", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Junior", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a30556ef292fd229cf1f7f8", "title" : "Junior Observability Engineer", "company" : "Miratech", "industry" : "Information Technology And Services", "salary" : { "min" : 600000.0, "max" : 950000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for an entry-level Junior Observability Engineer in Chennai, India, adjusted for the technology industry and company size." }, "location" : "Chennai, IN", "locations" : [ "Chennai", "IN" ], "timestamp" : "2026-06-16T08:14:52.944", "fingerprint" : "bc214d55dfa27fe444434cf03eb4dce1a9c86c7aa85c965494d450770a007efa", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Miratech1/744000131874190-devops-engineer-with-splunk", "externalId" : "744000131874190", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Chennai", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "13.0836939,80.2701860" } ], "locationText" : "Chennai, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "mid", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Miratech helps visionaries change the world. We are a global IT services and consulting company that brings together enterprise and start-up innovation. Today, we support digital transformation for some of the world's largest enterprises. By partnering with both large and small players, we stay at the leading edge of technology, remain nimble even as a global leader, and create technology that helps our clients further enhance their business. We are a valuesdriven organization and our culture of Relentless Performance has enabled over 99% of Miratech's engagements to succeed by meeting or exceeding our scope, schedule, and/or budget objectives since our inception in 1989. Miratech has coverage across 5 continents and operates in 25 countries around the world. Miratech retains nearly 1000 full-time professionals, and our annual growth rate exceeds 25%. We are looking for a Junior Observability Engineer to design, implement, and optimize enterprise observability solutions across applications, infrastructure, and cloud environments. This role focuses on monitoring, telemetry, automation, reliability engineering, and AIOps capabilities to improve system visibility, operational efficiency, and service reliability. The ideal candidate will have hands-on experience with observability platforms, cloud technologies, automation, and incident management practices while collaborating with engineering and operations teams to establish observability standards and best practices. Responsibilities * Design and implement end-to-end observability solutions across applications, infrastructure, and cloud environments. * Develop dashboards, alerts, and telemetry frameworks to provide real-time visibility into system health and performance. * Build automation solutions to eliminate repetitive operational tasks and improve efficiency. * Enable runbook automation, self-healing capabilities, and automated incident triage workflows. * Define and implement SLIs, SLOs, and alerting strategies to improve service reliability. * Drive improvements in MTTD and MTTR through actionable alerts and telemetry-driven insights. * Implement proactive monitoring, anomaly detection, and predictive alerting to identify issues before customer impact. * Leverage AIOps capabilities for alert correlation and intelligent incident response. * Integrate observability platforms with CI/CD pipelines, cloud services, and ITSM tools such as ServiceNow. * Collaborate with engineering, product, and operations teams to establish observability standards and operational readiness practices. ## Qualifications * 3+ years of experience in Observability Engineering, Site Reliability Engineering, or related domains. * Hands-on experience with observability platforms such as Splunk, Dynatrace, Grafana, and OpenTelemetry. * Strong expertise in AWS and GCP knowledge, with familiarity with cloud-native architectures. * Proficiency in Python for automation and operational tooling. * Experience implementing metrics, logs, events, and distributed tracing (MELT) across distributed systems. * Hands-on experience with Terraform and Infrastructure as Code practices. * Strong understanding of SLIs, SLOs, alerting strategies, and incident response frameworks. * Excellent troubleshooting, communication, and collaboration skills. * Bachelor's degree in Computer Science, Information Technology, or a related field (or equivalent experience). Nice to Have * Experience with AIOps platforms and intelligent alerting solutions. * Knowledge of Kubernetes and containerized environments. * Experience integrating observability tools with ServiceNow and CI/CD ecosystems. * AWS, GCP, Observability, or SRE-related certifications. We offer: * Culture of Relentless Performance : join an unstoppable technology development team with a 99% project success rate and more than 30% year-over-year revenue growth. * Competitive Pay and Benefits : enjoy a comprehensive compensation and benefits package, including health insurance, language courses, and a relocation program. * Work From Anywhere Culture : make the most of the flexibility that comes with remote work. * Growth Mindset : reap the benefits of a range of professional development opportunities, including certification programs, mentorship and talent investment programs, internal mobility and internship opportunities. * Global Impact : collaborate on impactful projects for top global clients and shape the future of industries. * Welcoming Multicultural Environment : be a part of a dynamic, global team and thrive in an inclusive and supportive work environment with open communication and regular team-building company social events. * Social Sustainability Values : join our sustainable business practices focused on five pillars, including IT education, community empowerment, fair operating practices, environmental sustainability, and gender equality. Miratech is an equal opportunity employer and does not discriminate against any employee or applicant for employment on the basis of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or any other protected status under applicable law. ## Additional Information All your information will be kept confidential according to EEO guidelines.", "summaryDescription" : "Junior Observability Engineer at Miratech", "postedDate" : "2026-06-12T11:13:12.000", "createdAt" : "2026-06-15T23:34:31.012", "lastUpdated" : "2026-06-16T08:14:52.944", "ingestTimestamp" : "2026-06-15T23:34:31.012", "mongoId" : "6a30556ef292fd229cf1f7f8", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Junior", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a30556ef292fd229cf1f7f9", "title" : "Junior Observability Engineer", "company" : "Miratech", "industry" : "Information Technology And Services", "salary" : { "min" : 600000.0, "max" : 900000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for an entry-level Junior Observability Engineer in Ahmedabad, India, adjusted for the technology industry and full-time employment." }, "location" : "Ahmedabad, IN", "locations" : [ "Ahmedabad", "IN" ], "timestamp" : "2026-06-16T08:08:22.078", "fingerprint" : "08155d0150a0de387e72ff1a589c82d5b23454d49676e270792bc3a5966791b7", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Miratech1/744000131874691-devops-engineer-with-splunk", "externalId" : "744000131874691", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Ahmedabad", "state" : "Gujarat", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "23.0215374,72.5800568" } ], "locationText" : "Ahmedabad, Gujarat, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "mid", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Miratech helps visionaries change the world. We are a global IT services and consulting company that brings together enterprise and start-up innovation. Today, we support digital transformation for some of the world's largest enterprises. By partnering with both large and small players, we stay at the leading edge of technology, remain nimble even as a global leader, and create technology that helps our clients further enhance their business. We are a valuesdriven organization and our culture of Relentless Performance has enabled over 99% of Miratech's engagements to succeed by meeting or exceeding our scope, schedule, and/or budget objectives since our inception in 1989. Miratech has coverage across 5 continents and operates in 25 countries around the world. Miratech retains nearly 1000 full-time professionals, and our annual growth rate exceeds 25%. We are looking for a Junior Observability Engineer to design, implement, and optimize enterprise observability solutions across applications, infrastructure, and cloud environments. This role focuses on monitoring, telemetry, automation, reliability engineering, and AIOps capabilities to improve system visibility, operational efficiency, and service reliability. The ideal candidate will have hands-on experience with observability platforms, cloud technologies, automation, and incident management practices while collaborating with engineering and operations teams to establish observability standards and best practices. Responsibilities * Design and implement end-to-end observability solutions across applications, infrastructure, and cloud environments. * Develop dashboards, alerts, and telemetry frameworks to provide real-time visibility into system health and performance. * Build automation solutions to eliminate repetitive operational tasks and improve efficiency. * Enable runbook automation, self-healing capabilities, and automated incident triage workflows. * Define and implement SLIs, SLOs, and alerting strategies to improve service reliability. * Drive improvements in MTTD and MTTR through actionable alerts and telemetry-driven insights. * Implement proactive monitoring, anomaly detection, and predictive alerting to identify issues before customer impact. * Leverage AIOps capabilities for alert correlation and intelligent incident response. * Integrate observability platforms with CI/CD pipelines, cloud services, and ITSM tools such as ServiceNow. * Collaborate with engineering, product, and operations teams to establish observability standards and operational readiness practices. ## Qualifications * 3+ years of experience in Observability Engineering, Site Reliability Engineering, or related domains. * Hands-on experience with observability platforms such as Splunk, Dynatrace, Grafana, and OpenTelemetry. * Strong expertise in AWS and GCP knowledge, with familiarity with cloud-native architectures. * Proficiency in Python for automation and operational tooling. * Experience implementing metrics, logs, events, and distributed tracing (MELT) across distributed systems. * Hands-on experience with Terraform and Infrastructure as Code practices. * Strong understanding of SLIs, SLOs, alerting strategies, and incident response frameworks. * Excellent troubleshooting, communication, and collaboration skills. * Bachelor's degree in Computer Science, Information Technology, or a related field (or equivalent experience). Nice to Have * Experience with AIOps platforms and intelligent alerting solutions. * Knowledge of Kubernetes and containerized environments. * Experience integrating observability tools with ServiceNow and CI/CD ecosystems. * AWS, GCP, Observability, or SRE-related certifications. We offer: * Culture of Relentless Performance : join an unstoppable technology development team with a 99% project success rate and more than 30% year-over-year revenue growth. * Competitive Pay and Benefits : enjoy a comprehensive compensation and benefits package, including health insurance, language courses, and a relocation program. * Work From Anywhere Culture : make the most of the flexibility that comes with remote work. * Growth Mindset : reap the benefits of a range of professional development opportunities, including certification programs, mentorship and talent investment programs, internal mobility and internship opportunities. * Global Impact : collaborate on impactful projects for top global clients and shape the future of industries. * Welcoming Multicultural Environment : be a part of a dynamic, global team and thrive in an inclusive and supportive work environment with open communication and regular team-building company social events. * Social Sustainability Values : join our sustainable business practices focused on five pillars, including IT education, community empowerment, fair operating practices, environmental sustainability, and gender equality. Miratech is an equal opportunity employer and does not discriminate against any employee or applicant for employment on the basis of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or any other protected status under applicable law. ## Additional Information All your information will be kept confidential according to EEO guidelines.", "summaryDescription" : "Junior Observability Engineer at Miratech", "postedDate" : "2026-06-12T11:12:36.000", "createdAt" : "2026-06-15T23:38:36.333", "lastUpdated" : "2026-06-16T08:08:22.078", "ingestTimestamp" : "2026-06-15T23:38:36.333", "mongoId" : "6a30556ef292fd229cf1f7f9", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Junior", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a30556ef292fd229cf1f7fa", "title" : "Junior Observability Engineer", "company" : "Miratech", "industry" : "Information Technology And Services", "salary" : { "min" : 650000.0, "max" : 1100000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for an entry-level Junior Observability Engineer in Hyderabad, India, adjusted for the technology industry and company size." }, "location" : "Hyderabad, IN", "locations" : [ "Hyderabad", "IN" ], "timestamp" : "2026-06-16T10:10:57.192", "fingerprint" : "2ff2106061299ab2707c93daa2370fdd3eb424a1a00a67771e2d0204b84dd514", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Miratech1/744000131874800-devops-engineer-with-splunk", "externalId" : "744000131874800", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Hyderabad", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "17.3605890,78.4740613" } ], "locationText" : "Hyderabad, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "mid", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Miratech helps visionaries change the world. We are a global IT services and consulting company that brings together enterprise and start-up innovation. Today, we support digital transformation for some of the world's largest enterprises. By partnering with both large and small players, we stay at the leading edge of technology, remain nimble even as a global leader, and create technology that helps our clients further enhance their business. We are a valuesdriven organization and our culture of Relentless Performance has enabled over 99% of Miratech's engagements to succeed by meeting or exceeding our scope, schedule, and/or budget objectives since our inception in 1989. Miratech has coverage across 5 continents and operates in 25 countries around the world. Miratech retains nearly 1000 full-time professionals, and our annual growth rate exceeds 25%. We are looking for a Junior Observability Engineer to design, implement, and optimize enterprise observability solutions across applications, infrastructure, and cloud environments. This role focuses on monitoring, telemetry, automation, reliability engineering, and AIOps capabilities to improve system visibility, operational efficiency, and service reliability. The ideal candidate will have hands-on experience with observability platforms, cloud technologies, automation, and incident management practices while collaborating with engineering and operations teams to establish observability standards and best practices. Responsibilities * Design and implement end-to-end observability solutions across applications, infrastructure, and cloud environments. * Develop dashboards, alerts, and telemetry frameworks to provide real-time visibility into system health and performance. * Build automation solutions to eliminate repetitive operational tasks and improve efficiency. * Enable runbook automation, self-healing capabilities, and automated incident triage workflows. * Define and implement SLIs, SLOs, and alerting strategies to improve service reliability. * Drive improvements in MTTD and MTTR through actionable alerts and telemetry-driven insights. * Implement proactive monitoring, anomaly detection, and predictive alerting to identify issues before customer impact. * Leverage AIOps capabilities for alert correlation and intelligent incident response. * Integrate observability platforms with CI/CD pipelines, cloud services, and ITSM tools such as ServiceNow. * Collaborate with engineering, product, and operations teams to establish observability standards and operational readiness practices. ## Qualifications * 3+ years of experience in Observability Engineering, Site Reliability Engineering, or related domains. * Hands-on experience with observability platforms such as Splunk, Dynatrace, Grafana, and OpenTelemetry. * Strong expertise in AWS and GCP knowledge, with familiarity with cloud-native architectures. * Proficiency in Python for automation and operational tooling. * Experience implementing metrics, logs, events, and distributed tracing (MELT) across distributed systems. * Hands-on experience with Terraform and Infrastructure as Code practices. * Strong understanding of SLIs, SLOs, alerting strategies, and incident response frameworks. * Excellent troubleshooting, communication, and collaboration skills. * Bachelor's degree in Computer Science, Information Technology, or a related field (or equivalent experience). Nice to Have * Experience with AIOps platforms and intelligent alerting solutions. * Knowledge of Kubernetes and containerized environments. * Experience integrating observability tools with ServiceNow and CI/CD ecosystems. * AWS, GCP, Observability, or SRE-related certifications. We offer: * Culture of Relentless Performance : join an unstoppable technology development team with a 99% project success rate and more than 30% year-over-year revenue growth. * Competitive Pay and Benefits : enjoy a comprehensive compensation and benefits package, including health insurance, language courses, and a relocation program. * Work From Anywhere Culture : make the most of the flexibility that comes with remote work. * Growth Mindset : reap the benefits of a range of professional development opportunities, including certification programs, mentorship and talent investment programs, internal mobility and internship opportunities. * Global Impact : collaborate on impactful projects for top global clients and shape the future of industries. * Welcoming Multicultural Environment : be a part of a dynamic, global team and thrive in an inclusive and supportive work environment with open communication and regular team-building company social events. * Social Sustainability Values : join our sustainable business practices focused on five pillars, including IT education, community empowerment, fair operating practices, environmental sustainability, and gender equality. Miratech is an equal opportunity employer and does not discriminate against any employee or applicant for employment on the basis of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or any other protected status under applicable law. ## Additional Information All your information will be kept confidential according to EEO guidelines.", "summaryDescription" : "Junior Observability Engineer at Miratech", "postedDate" : "2026-06-12T11:11:54.000", "createdAt" : "2026-06-15T23:38:51.495", "lastUpdated" : "2026-06-16T10:10:57.192", "ingestTimestamp" : "2026-06-15T23:38:51.495", "mongoId" : "6a30556ef292fd229cf1f7fa", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Junior", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a30556ef292fd229cf1f7fb", "title" : "Junior Observability Engineer", "company" : "Miratech", "industry" : "Information Technology And Services", "salary" : { "min" : 750000.0, "max" : 1250000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for Junior Observability Engineer in Bengaluru, India, adjusted for entry-level experience and full-time onsite employment in the technology sector." }, "location" : "Bengaluru, IN", "locations" : [ "Bengaluru", "IN" ], "timestamp" : "2026-06-16T07:12:54.825", "fingerprint" : "247d9a947acbdc613e6ceca1e37ae9a48fce3dc2cf894a3bc927e8d3eb491f00", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Miratech1/744000131874659-devops-engineer-with-splunk", "externalId" : "744000131874659", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Bengaluru", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "12.9767936,77.5900820" } ], "locationText" : "Bengaluru, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "mid", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Miratech helps visionaries change the world. We are a global IT services and consulting company that brings together enterprise and start-up innovation. Today, we support digital transformation for some of the world's largest enterprises. By partnering with both large and small players, we stay at the leading edge of technology, remain nimble even as a global leader, and create technology that helps our clients further enhance their business. We are a valuesdriven organization and our culture of Relentless Performance has enabled over 99% of Miratech's engagements to succeed by meeting or exceeding our scope, schedule, and/or budget objectives since our inception in 1989. Miratech has coverage across 5 continents and operates in 25 countries around the world. Miratech retains nearly 1000 full-time professionals, and our annual growth rate exceeds 25%. We are looking for a Junior Observability Engineer to design, implement, and optimize enterprise observability solutions across applications, infrastructure, and cloud environments. This role focuses on monitoring, telemetry, automation, reliability engineering, and AIOps capabilities to improve system visibility, operational efficiency, and service reliability. The ideal candidate will have hands-on experience with observability platforms, cloud technologies, automation, and incident management practices while collaborating with engineering and operations teams to establish observability standards and best practices. Responsibilities * Design and implement end-to-end observability solutions across applications, infrastructure, and cloud environments. * Develop dashboards, alerts, and telemetry frameworks to provide real-time visibility into system health and performance. * Build automation solutions to eliminate repetitive operational tasks and improve efficiency. * Enable runbook automation, self-healing capabilities, and automated incident triage workflows. * Define and implement SLIs, SLOs, and alerting strategies to improve service reliability. * Drive improvements in MTTD and MTTR through actionable alerts and telemetry-driven insights. * Implement proactive monitoring, anomaly detection, and predictive alerting to identify issues before customer impact. * Leverage AIOps capabilities for alert correlation and intelligent incident response. * Integrate observability platforms with CI/CD pipelines, cloud services, and ITSM tools such as ServiceNow. * Collaborate with engineering, product, and operations teams to establish observability standards and operational readiness practices. ## Qualifications * 3+ years of experience in Observability Engineering, Site Reliability Engineering, or related domains. * Hands-on experience with observability platforms such as Splunk, Dynatrace, Grafana, and OpenTelemetry. * Strong expertise in AWS and GCP knowledge, with familiarity with cloud-native architectures. * Proficiency in Python for automation and operational tooling. * Experience implementing metrics, logs, events, and distributed tracing (MELT) across distributed systems. * Hands-on experience with Terraform and Infrastructure as Code practices. * Strong understanding of SLIs, SLOs, alerting strategies, and incident response frameworks. * Excellent troubleshooting, communication, and collaboration skills. * Bachelor's degree in Computer Science, Information Technology, or a related field (or equivalent experience). Nice to Have * Experience with AIOps platforms and intelligent alerting solutions. * Knowledge of Kubernetes and containerized environments. * Experience integrating observability tools with ServiceNow and CI/CD ecosystems. * AWS, GCP, Observability, or SRE-related certifications. We offer: * Culture of Relentless Performance : join an unstoppable technology development team with a 99% project success rate and more than 30% year-over-year revenue growth. * Competitive Pay and Benefits : enjoy a comprehensive compensation and benefits package, including health insurance, language courses, and a relocation program. * Work From Anywhere Culture : make the most of the flexibility that comes with remote work. * Growth Mindset : reap the benefits of a range of professional development opportunities, including certification programs, mentorship and talent investment programs, internal mobility and internship opportunities. * Global Impact : collaborate on impactful projects for top global clients and shape the future of industries. * Welcoming Multicultural Environment : be a part of a dynamic, global team and thrive in an inclusive and supportive work environment with open communication and regular team-building company social events. * Social Sustainability Values : join our sustainable business practices focused on five pillars, including IT education, community empowerment, fair operating practices, environmental sustainability, and gender equality. Miratech is an equal opportunity employer and does not discriminate against any employee or applicant for employment on the basis of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or any other protected status under applicable law. ## Additional Information All your information will be kept confidential according to EEO guidelines.", "summaryDescription" : "Junior Observability Engineer at Miratech", "postedDate" : "2026-06-12T11:11:07.000", "createdAt" : "2026-06-15T23:36:32.805", "lastUpdated" : "2026-06-16T07:12:54.825", "ingestTimestamp" : "2026-06-15T23:36:32.805", "mongoId" : "6a30556ef292fd229cf1f7fb", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Junior", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a30556ef292fd229cf1f7fc", "title" : "Junior Observability Engineer", "company" : "Miratech", "industry" : "Information Technology And Services", "salary" : { "min" : 750000.0, "max" : 1200000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Mid-level Junior Observability Engineer in Delhi, India, adjusted for the Technology industry and company size." }, "location" : "Delhi, IN", "locations" : [ "Delhi", "IN" ], "timestamp" : "2026-06-16T07:10:09.413", "fingerprint" : "16ae4a93b7b8ac4840342d39b7a746ef0af7fc930bff978d007f2f4cd019003f", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Miratech1/744000131874570-devops-engineer-with-splunk", "externalId" : "744000131874570", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Delhi", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "28.6138954,77.2090057" } ], "locationText" : "Delhi, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "mid", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Miratech helps visionaries change the world. We are a global IT services and consulting company that brings together enterprise and start-up innovation. Today, we support digital transformation for some of the world's largest enterprises. By partnering with both large and small players, we stay at the leading edge of technology, remain nimble even as a global leader, and create technology that helps our clients further enhance their business. We are a valuesdriven organization and our culture of Relentless Performance has enabled over 99% of Miratech's engagements to succeed by meeting or exceeding our scope, schedule, and/or budget objectives since our inception in 1989. Miratech has coverage across 5 continents and operates in 25 countries around the world. Miratech retains nearly 1000 full-time professionals, and our annual growth rate exceeds 25%. We are looking for a Junior Observability Engineer to design, implement, and optimize enterprise observability solutions across applications, infrastructure, and cloud environments. This role focuses on monitoring, telemetry, automation, reliability engineering, and AIOps capabilities to improve system visibility, operational efficiency, and service reliability. The ideal candidate will have hands-on experience with observability platforms, cloud technologies, automation, and incident management practices while collaborating with engineering and operations teams to establish observability standards and best practices. Responsibilities * Design and implement end-to-end observability solutions across applications, infrastructure, and cloud environments. * Develop dashboards, alerts, and telemetry frameworks to provide real-time visibility into system health and performance. * Build automation solutions to eliminate repetitive operational tasks and improve efficiency. * Enable runbook automation, self-healing capabilities, and automated incident triage workflows. * Define and implement SLIs, SLOs, and alerting strategies to improve service reliability. * Drive improvements in MTTD and MTTR through actionable alerts and telemetry-driven insights. * Implement proactive monitoring, anomaly detection, and predictive alerting to identify issues before customer impact. * Leverage AIOps capabilities for alert correlation and intelligent incident response. * Integrate observability platforms with CI/CD pipelines, cloud services, and ITSM tools such as ServiceNow. * Collaborate with engineering, product, and operations teams to establish observability standards and operational readiness practices. ## Qualifications * 3+ years of experience in Observability Engineering, Site Reliability Engineering, or related domains. * Hands-on experience with observability platforms such as Splunk, Dynatrace, Grafana, and OpenTelemetry. * Strong expertise in AWS and GCP knowledge, with familiarity with cloud-native architectures. * Proficiency in Python for automation and operational tooling. * Experience implementing metrics, logs, events, and distributed tracing (MELT) across distributed systems. * Hands-on experience with Terraform and Infrastructure as Code practices. * Strong understanding of SLIs, SLOs, alerting strategies, and incident response frameworks. * Excellent troubleshooting, communication, and collaboration skills. * Bachelor's degree in Computer Science, Information Technology, or a related field (or equivalent experience). Nice to Have * Experience with AIOps platforms and intelligent alerting solutions. * Knowledge of Kubernetes and containerized environments. * Experience integrating observability tools with ServiceNow and CI/CD ecosystems. * AWS, GCP, Observability, or SRE-related certifications. We offer: * Culture of Relentless Performance : join an unstoppable technology development team with a 99% project success rate and more than 30% year-over-year revenue growth. * Competitive Pay and Benefits : enjoy a comprehensive compensation and benefits package, including health insurance, language courses, and a relocation program. * Work From Anywhere Culture : make the most of the flexibility that comes with remote work. * Growth Mindset : reap the benefits of a range of professional development opportunities, including certification programs, mentorship and talent investment programs, internal mobility and internship opportunities. * Global Impact : collaborate on impactful projects for top global clients and shape the future of industries. * Welcoming Multicultural Environment : be a part of a dynamic, global team and thrive in an inclusive and supportive work environment with open communication and regular team-building company social events. * Social Sustainability Values : join our sustainable business practices focused on five pillars, including IT education, community empowerment, fair operating practices, environmental sustainability, and gender equality. Miratech is an equal opportunity employer and does not discriminate against any employee or applicant for employment on the basis of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or any other protected status under applicable law. ## Additional Information All your information will be kept confidential according to EEO guidelines.", "summaryDescription" : "Junior Observability Engineer at Miratech", "postedDate" : "2026-06-12T11:10:24.000", "createdAt" : "2026-06-15T23:35:31.057", "lastUpdated" : "2026-06-16T07:10:09.413", "ingestTimestamp" : "2026-06-15T23:35:31.057", "mongoId" : "6a30556ef292fd229cf1f7fc", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Mid", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a30556ef292fd229cf1f7fd", "title" : "Junior Observability Engineer", "company" : "Miratech", "industry" : "Information Technology And Services", "salary" : { "min" : 750000.0, "max" : 1250000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for an entry-level Junior Observability Engineer in Mumbai, India, adjusted for the technology industry and full-time employment." }, "location" : "Mumbai, IN", "locations" : [ "Mumbai", "IN" ], "timestamp" : "2026-06-16T10:07:10.696", "fingerprint" : "a81076eda9b605c7a2dbc964686792a2a607c29b01d2e383f554cde2ee006912", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Miratech1/744000131873854-devops-engineer-with-splunk", "externalId" : "744000131873854", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Mumbai", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "19.0549990,72.8692035" } ], "locationText" : "Mumbai, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "mid", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Miratech helps visionaries change the world. We are a global IT services and consulting company that brings together enterprise and start-up innovation. Today, we support digital transformation for some of the world's largest enterprises. By partnering with both large and small players, we stay at the leading edge of technology, remain nimble even as a global leader, and create technology that helps our clients further enhance their business. We are a valuesdriven organization and our culture of Relentless Performance has enabled over 99% of Miratech's engagements to succeed by meeting or exceeding our scope, schedule, and/or budget objectives since our inception in 1989. Miratech has coverage across 5 continents and operates in 25 countries around the world. Miratech retains nearly 1000 full-time professionals, and our annual growth rate exceeds 25%. We are looking for a Junior Observability Engineer to design, implement, and optimize enterprise observability solutions across applications, infrastructure, and cloud environments. This role focuses on monitoring, telemetry, automation, reliability engineering, and AIOps capabilities to improve system visibility, operational efficiency, and service reliability. The ideal candidate will have hands-on experience with observability platforms, cloud technologies, automation, and incident management practices while collaborating with engineering and operations teams to establish observability standards and best practices. Responsibilities * Design and implement end-to-end observability solutions across applications, infrastructure, and cloud environments. * Develop dashboards, alerts, and telemetry frameworks to provide real-time visibility into system health and performance. * Build automation solutions to eliminate repetitive operational tasks and improve efficiency. * Enable runbook automation, self-healing capabilities, and automated incident triage workflows. * Define and implement SLIs, SLOs, and alerting strategies to improve service reliability. * Drive improvements in MTTD and MTTR through actionable alerts and telemetry-driven insights. * Implement proactive monitoring, anomaly detection, and predictive alerting to identify issues before customer impact. * Leverage AIOps capabilities for alert correlation and intelligent incident response. * Integrate observability platforms with CI/CD pipelines, cloud services, and ITSM tools such as ServiceNow. * Collaborate with engineering, product, and operations teams to establish observability standards and operational readiness practices. ## Qualifications * 3+ years of experience in Observability Engineering, Site Reliability Engineering, or related domains. * Hands-on experience with observability platforms such as Splunk, Dynatrace, Grafana, and OpenTelemetry. * Strong expertise in AWS and GCP knowledge, with familiarity with cloud-native architectures. * Proficiency in Python for automation and operational tooling. * Experience implementing metrics, logs, events, and distributed tracing (MELT) across distributed systems. * Hands-on experience with Terraform and Infrastructure as Code practices. * Strong understanding of SLIs, SLOs, alerting strategies, and incident response frameworks. * Excellent troubleshooting, communication, and collaboration skills. * Bachelor's degree in Computer Science, Information Technology, or a related field (or equivalent experience). Nice to Have * Experience with AIOps platforms and intelligent alerting solutions. * Knowledge of Kubernetes and containerized environments. * Experience integrating observability tools with ServiceNow and CI/CD ecosystems. * AWS, GCP, Observability, or SRE-related certifications. We offer: * Culture of Relentless Performance : join an unstoppable technology development team with a 99% project success rate and more than 30% year-over-year revenue growth. * Competitive Pay and Benefits : enjoy a comprehensive compensation and benefits package, including health insurance, language courses, and a relocation program. * Work From Anywhere Culture : make the most of the flexibility that comes with remote work. * Growth Mindset : reap the benefits of a range of professional development opportunities, including certification programs, mentorship and talent investment programs, internal mobility and internship opportunities. * Global Impact : collaborate on impactful projects for top global clients and shape the future of industries. * Welcoming Multicultural Environment : be a part of a dynamic, global team and thrive in an inclusive and supportive work environment with open communication and regular team-building company social events. * Social Sustainability Values : join our sustainable business practices focused on five pillars, including IT education, community empowerment, fair operating practices, environmental sustainability, and gender equality. Miratech is an equal opportunity employer and does not discriminate against any employee or applicant for employment on the basis of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or any other protected status under applicable law. ## Additional Information All your information will be kept confidential according to EEO guidelines.", "summaryDescription" : "Junior Observability Engineer at Miratech", "postedDate" : "2026-06-12T11:09:48.000", "createdAt" : "2026-06-15T23:44:04.140", "lastUpdated" : "2026-06-16T10:07:10.696", "ingestTimestamp" : "2026-06-15T23:44:04.140", "mongoId" : "6a30556ef292fd229cf1f7fd", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Junior", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2cadc474d8ee00a09d398d", "title" : "Distributed Systems Engineer", "company" : "ThisWay Global", "industry" : "Information Technology and Services", "salary" : { "min" : 155000.0, "max" : 215000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Distributed Systems Engineer in the US technology sector, adjusted for remote work and company size." }, "location" : "Remote", "locations" : [ "Remote" ], "timestamp" : "2026-06-15T03:30:56.562", "fingerprint" : "fd8ba4b0e92b1f00a57e8a4c408a7527a37d4db8ab5e31acbbb58e9e3aabd501", "source" : "workable", "language" : "en", "applyUrl" : "https://apply.workable.com/j/3E80017B40/apply", "externalId" : "3E80017B40", "industryFunction" : { }, "locationPoint" : "39.8283,-98.5795", "structuredLocations" : [ { "country" : "United States", "continent" : "na", "workMode" : "remote" } ], "locationText" : "United States", "employmentType" : "FULL_TIME", "technicalSkills" : "Rust, Go, NVIDIA NVL72, GB300", "professionalSkills" : [ "Systems programming", "System design", "Performance optimization" ], "hardSkillsList" : [ "Fault tolerance", "Eventual consistency", "Memory management", "I/O optimization", "Concurrency issues", "Distributed coordination" ], "hardSkills" : [ { "name" : "Fault tolerance", "level" : "intermediate" }, { "name" : "Eventual consistency", "level" : "intermediate" }, { "name" : "Memory management", "level" : "intermediate" }, { "name" : "I/O optimization", "level" : "intermediate" }, { "name" : "Concurrency issues", "level" : "intermediate" }, { "name" : "Distributed coordination", "level" : "intermediate" } ], "majorSkills" : "Distributed systems, Exascale computing, AI infrastructure", "majorSkillsList" : [ "Distributed systems", "Exascale computing", "AI infrastructure" ], "coreResponsibilities" : "Design distributed systems, Implement fault-tolerant communication, Write maintainable code, Debug system behavior, Contribute to systems in Rust, Work with system-level concerns, Optimize performance, Debug concurrency issues, Design APIs, Identify and reduce tight coupling, Diagnose and resolve failures, Design and implement secure solutions, Collaborate with engineers, Contribute to resolving issues, Continue developing expertise", "teamCollaboration" : "Collaborate with engineers; Collaborate with computer scientists", "domainKnowledge" : "Distributed systems; AI; Exascale computing; HPC infrastructure; Operating systems internals; Compiler internals; Fault tolerance; File system architecture; Trusted systems", "domainList" : [ "distributed-systems", "ai", "exascale-computing", "hpc-infrastructure", "operating-systems-internals", "compiler-internals", "fault-tolerance", "file-system-architecture", "trusted-systems" ], "domainSpecificKnowledge" : [ "Distributed systems", "AI", "Exascale computing", "HPC infrastructure", "Operating systems internals", "Compiler internals", "Fault tolerance", "File system architecture", "Trusted systems" ], "continuousLearning" : "Developing expertise", "problemSolvingSkills" : "Troubleshooting; Root cause analysis", "qualificationsBasic" : "Experience building distributed systems, Production experience developing systems in Rust or Go, Understanding of distributed systems failure modes, Knowledge of consistency models, Experience designing APIs, Experience working within established architectures, Understanding of systems-level concepts", "qualificationsPreferred" : "Experience with HPC environments, Exposure to operating systems internals, Experience with edge computing, Familiarity with message queues, Exposure to consensus algorithms, Experience with concurrency, Experience contributing to developer tooling", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "ThisWay Global is looking for a Distributed Systems Engineer in a remote role within the United States. ThisWay Global, Inc. is an AI-first technology company headquartered in Texas, operating at the intersection of artificial intelligence, data center infrastructure, and workforce solutions. The company operates across three primary business areas: * **ADCAP — AI & Data Center Acceleration Platform:** A data center development and operations platform supporting accelerated deployment timelines and NVIDIA NVL72/GB300 GPU clusters. * **Amalgamy.ai — AI Orchestration Software:** An enterprise AI orchestration platform focused on GPU and compute utilization across AI environments. * **Staffing & Workforce Solutions:** AI-powered talent matching solutions connecting employers with candidates at scale. This role focuses on building foundational distributed systems and operational infrastructure that support AI and exascale computing environments. The work emphasizes systems programming, distributed architecture, fault tolerance, and HPC-grade reliability. **Location:** Remote – United States **Department:** Engineering **Employment Type:** Full-Time, Exempt ### Responsibilities * Design and build distributed systems that tolerate latency, bandwidth constraints, and intermittent connectivity. * Implement fault-tolerant communication strategies, retry logic, backpressure, caching, and eventual consistency patterns. * Write maintainable, resilient, and tested code following development standards and methodologies. * Debug and improve system behavior, including networking and distributed coordination issues. * Contribute to systems written primarily in Rust. * Work with system-level concerns including scheduling, memory management, I/O optimization, storage hierarchy management, and system reliability. * Optimize performance and memory usage in resource-constrained environments. * Debug concurrency issues and distributed coordination challenges. * Design and maintain APIs and communication layers between distributed components. * Identify and reduce tight coupling across services and systems. * Diagnose and resolve cross-system failures in production environments. * Design and implement secure, reliable solutions aligned with engineering standards. * Collaborate with engineers and computer scientists on operating systems internals, compiler internals, fault tolerance, file system architecture, and trusted systems. * Contribute to resolving architectural and systemic issues. * Continue developing expertise in distributed systems, HPC infrastructure, and related tooling. **Requirements** * Experience building distributed systems in environments with low bandwidth, high latency, or unreliable communication links. * Production experience developing systems in Rust or Go. * Understanding of distributed systems failure modes and mitigation strategies. * Knowledge of consistency models, coordination strategies, and state replication. * Experience designing APIs and communication layers between distributed components. * Experience working within established architectures and delivering production-quality components. * Understanding of systems-level concepts including durability, reliability, and operational behavior. * Ability to work independently while collaborating with technical leadership. ### Preferred Qualifications * Experience with HPC environments, exascale computing, or AI/ML infrastructure. * Exposure to operating systems internals, compiler design, or language runtimes. * Experience with edge computing or constrained network environments. * Familiarity with message queues, event-driven systems, or streaming architectures. * Exposure to consensus algorithms or distributed coordination primitives. * Experience with concurrency, memory management, or performance optimization in production systems. * Experience contributing to developer tooling, internal platforms, or infrastructure-layer components. **Benefits** * Remote work within the United States. * Opportunity to work on distributed systems supporting AI and exascale workloads. * Collaboration with engineers experienced in operating systems internals, compiler internals, fault tolerance, file system architecture, and trusted systems. * Exposure to AI infrastructure, HPC, and large-scale distributed computing environments.", "summaryDescription" : "Distributed Systems Engineer at ThisWay Global. Skills: Distributed systems, Exascale computing, AI infrastructure. Design distributed systems. Implement fault-tolerant communication", "postedDate" : "2026-06-12T00:00:00.000", "createdAt" : "2026-06-14T00:15:09.474", "lastUpdated" : "2026-06-15T03:30:56.562", "ingestTimestamp" : "2026-06-14T00:15:09.474", "mongoId" : "6a2cadc474d8ee00a09d398d", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "sourceUrl" : "https://apply.workable.com/j/3E80017B40", "salaryAnnualMin" : 155000, "salaryAnnualMax" : 215000, "salaryBand" : "150k-200k", "hasSalary" : true, "allSkills" : [ "Fault tolerance", "Eventual consistency", "Memory management", "I/O optimization", "Concurrency issues", "Distributed coordination", "Distributed systems", "Exascale computing", "AI infrastructure", "Systems programming", "System design", "Performance optimization", "AI", "HPC infrastructure", "Operating systems internals", "Compiler internals", "File system architecture", "Trusted systems" ], "skillCount" : 18, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "mid", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2ca06974d8ee00a09a228b", "title" : "Infrastructure Tooling & Observability Engineer", "industry" : "Infra Ops", "salary" : { "min" : 85000.0, "max" : 120000.0, "currency" : "GBP", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Infrastructure Tooling & Observability Engineer in London, UK, adjusted for the technology industry." }, "location" : "London", "locations" : [ "London" ], "certifications" : [ "Kubernetes Certified Administrator", "CompTIA+ Security", "LPI/LPIC certification" ], "timestamp" : "2026-06-15T13:51:09.906", "fingerprint" : "866bafc7bba69c00912afc26a06e8a482c28f3154b3c0e18e06ddb41cfdc93fa", "source" : "ashby", "language" : "en", "applyUrl" : "https://jobs.ashbyhq.com/radiant/d14f4cd4-cb51-4b77-8af2-917ae28f7119/application", "externalId" : "d14f4cd4-cb51-4b77-8af2-917ae28f7119", "industryFunction" : { }, "structuredLocations" : [ { "city" : "London", "country" : "United Kingdom", "continent" : "eu", "source" : "llm", "workMode" : "onsite", "geo" : "51.5074456,-0.1277653" } ], "locationText" : "London, United Kingdom", "employmentType" : "FULL_TIME", "domainKnowledge" : "AI workloads; HPC workloads; GPU fleet; High-volume telemetry; Networking layers; Platform layers; Distributed environments; Cloud-native observability", "domainList" : [ "ai-workloads", "hpc-workloads", "gpu-fleet", "high-volume-telemetry", "networking-layers", "platform-layers", "distributed-environments", "cloud-native-observability" ], "domainSpecificKnowledge" : [ "AI workloads", "HPC workloads", "GPU fleet", "High-volume telemetry", "Networking layers", "Platform layers", "Distributed environments", "Cloud-native observability" ], "remoteFriendly" : true, "workSiteFlexibility" : "Onsite", "rawDescription" : "ABOUT US We’re a fast-growing GPU-as-a-Service provider, delivering scalable, high-performance compute infrastructure purpose-built for AI and HPC workloads. Operating across global data centres, we run mission-critical environments where uptime, throughput, and ultra-low latency are non-negotiable. ROLE OVERVIEW We are seeking an Infrastructure Tooling & Observability Engineer to act as a key engineering force within our global Infrastructure Operations organisation. Working closely with our SRE teams, you will translate high-level reliability objectives into scalable, production-ready systems that directly improve the resilience, efficiency, and performance of our global infrastructure. This role goes beyond traditional monitoring. You will help design and build the internal control plane that enables operations at scale across a rapidly growing GPU fleet. Your work will focus on transforming complex, high-volume telemetry—spanning logs, metrics, and events across HPC, networking, and platform layers—into actionable insight that drives operational excellence and proactive reliability. A core part of your responsibility will be developing intelligent observability and automation systems, including advanced alerting strategies, anomaly detection, and AI-driven tooling that reduces L1/L2 escalations and removes operational toil. You will also contribute to Continual Service Improvement (CSI) initiatives by building frameworks for reliability measurement, automated remediation, and system health evaluation. In addition, you will play a central role in turning SRE reliability initiatives into scalable engineering solutions. This includes designing and delivering capabilities such as inventory management systems, performance testing frameworks, and automated performance result collection. You will also help eliminate manual workflows involved in onboarding new regions, facilities, and clusters, embedding automation and standardisation into every stage of infrastructure deployment. As the organisation scales, you will act as a critical interface between operations and engineering teams. You will evaluate and mature internally built tooling—from capacity planning systems to autonomous remediation pipelines—and help integrate these capabilities into core infrastructure platforms to ensure consistent, high-performance, and highly reliable global operations. WHAT’S IN IT FOR YOU? Join a team building the internal platforms that enable large-scale infrastructure to operate reliably, efficiently, and at speed. As an Infrastructure Tooling & Observability Engineer, you will design and develop the systems that power visibility, automation, and operational intelligence across complex distributed environments. This role goes beyond traditional monitoring. You will build the internal control plane that transforms high-volume telemetry—logs, metrics, and events—into actionable insight for engineering and operations teams. Your work will improve observability across infrastructure systems, strengthen signal quality, and help teams understand and respond to system behaviour in real time. Working closely with SRE and infrastructure engineering teams, you will translate reliability goals into scalable, production-grade tooling. This includes frameworks for observability, alerting, anomaly detection, capacity planning, and service health tracking. A key focus of the role is automation. You will help eliminate manual processes across infrastructure operations, including environment provisioning, cluster onboarding, inventory management, and recurring operational workflows. You will also contribute to performance engineering initiatives, building tooling for testing, benchmarking, and automated results collection at scale. You will play a central role in turning SRE reliability initiatives into reusable engineering solutions, including automated remediation systems and tooling that reduces operational toil while improving system resilience. You can also expect: Exposure to large-scale distributed infrastructure systems Opportunities to shape foundational internal platforms A collaborative, engineering-led culture with strong ownership High-impact work spanning observability, automation, and reliability Close partnership with SRE and infrastructure engineering teams A fast-moving environment where tooling directly improves operational performance KEY RESPONSIBILITIES - Design, build, and evolve internal tooling and observability platforms that support large-scale infrastructure operations across distributed environments. - Develop systems that turn high-volume telemetry (logs, metrics, events) into actionable insight, improving visibility, alerting quality, and operational decision-making. - Translate SRE reliability requirements into scalable, production-ready software solutions, including automation for incident detection, prevention, and remediation. - Drive automation across infrastructure operations, reducing manual effort in areas such as environment provisioning, cluster onboarding, inventory management, and lifecycle workflows. - Build tooling for capacity management, performance testing, benchmarking, and automated collection and analysis of results. - Contribute to Continual Service Improvement (CSI) initiatives by identifying operational inefficiencies and delivering durable engineering solutions. - Work closely with SRE and infrastructure engineering teams to embed observability and reliability into core platform workflows. - Interface with Platform Engineering teams to ensure tooling aligns with broader orchestration and infrastructure strategy. - Integrate and extend existing systems written in Ruby/Rails and Go, contributing to a consistent and maintainable engineering ecosystem. - Develop and maintain automation workflows using Ansible and AWX. - Support CI/CD-driven operational tooling, including GitHub Actions and self-hosted runners. ESSENTIAL SKILLS & EXPERIENCE - Degree in Computer Science/Software Engineering, or equivalent experience - 6–8 years of experience in infrastructure engineering, DevOps, SRE, and/or software engineering roles, with a strong focus on operational systems. - Proven experience in at least one recent DevOps or software engineering role, building or maintaining production infrastructure tooling or platform systems. - Experience working in large-scale or distributed infrastructure environments (hyperscale, enterprise, or similarly complex systems). - Strong programming ability in at least one of: Ruby (Rails), Go, or similar systems languages, with willingness and ability to work across multiple languages and codebases. - Hands-on experience with infrastructure automation tools such as Ansible and orchestration platforms such as AWX. - Strong experience with observability systems, including the Grafana stack (Prometheus, Loki, Mimir, and Grafana Alloy). - Familiarity with low-level telemetry and infrastructure protocols such as SNMP and syslog. - Experience working with Kubernetes or similar orchestration platforms in production environments. - Understanding of API design and integration patterns, particularly REST-based services and service-to-service communication. - Experience building and maintaining CI/CD pipelines, including GitHub Actions and self-hosted runners. - Strong understanding of operational reliability concepts, including monitoring, alerting, capacity planning, and incident response. - Comfortable working closely with SRE, Platform Engineering, and infrastructure teams to translate operational needs into maintainable software systems. Preferred Qualifications - Kubernetes Certified Administrator - Cloud-native observability training courses, attendance at industry conferences in this field - CompTIA+ Security Qualifications - LPI/LPIC certification", "summaryDescription" : "Infrastructure Tooling & Observability Engineer", "createdAt" : "2026-06-14T05:02:12.180", "lastUpdated" : "2026-06-15T13:51:09.906", "ingestTimestamp" : "2026-06-14T05:02:12.180", "mongoId" : "6a2ca06974d8ee00a09a228b", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "75k-100k", "hasSalary" : false, "allSkills" : [ "AI workloads", "HPC workloads", "GPU fleet", "High-volume telemetry", "Networking layers", "Platform layers", "Distributed environments", "Cloud-native observability", "Kubernetes Certified Administrator", "CompTIA+ Security", "LPI/LPIC certification" ], "skillCount" : 11, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 0.6666667, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2c95ab74d8ee00a098db03", "title" : "Senior Software Engineer - Distributed Systems", "company" : "Fanatics Betting & Gaming", "industry" : "FinTech", "salary" : { "min" : 152000.0, "max" : 200000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : false }, "location" : "New York, New York, United States", "locations" : [ "New York", "New York", "United States" ], "timestamp" : "2026-06-15T06:37:08.299", "fingerprint" : "f7686d69da435593ad262e2bd01ac204b8b8cf21b505563436661f6d0de96422", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.greenhouse.io/fanaticsfbg/jobs/4254293009", "externalId" : "4254293009", "industryFunction" : { }, "structuredLocations" : [ { "city" : "New York", "state" : "New York", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "40.7127281,-74.0060152" } ], "locationText" : "New York, New York, United States", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Kotlin, Java, Spring Boot, REST, GRPC, Protobuf, Kafka, Redpanda, Pub Sub, Postgres, Redis, Redis PubSub, Kubernetes, Helm, Terraform, AWS", "professionalSkills" : [ "API design", "System design", "Platform strategy", "Technical leadership", "Build vs buy" ], "hardSkillsList" : [ "Distributed systems", "High-throughput systems", "Low-latency design", "Event pipelines", "Data integrity", "Cache coherence", "Exactly-once processing", "Backpressure handling", "Circuit breaking", "Idempotent retry logic", "Graceful degradation", "Fan-out problem", "Schema evolution", "Testing practices", "Deployment patterns", "Production reliability", "On-call triage", "Durable fixes", "Technical direction", "Architectural decisions", "Success metrics", "Latency budgets", "Throughput targets" ], "softSkillsList" : [ "Leadership", "Mentoring" ], "hardSkills" : [ { "name" : "Distributed systems", "level" : "intermediate" }, { "name" : "High-throughput systems", "level" : "intermediate" }, { "name" : "Low-latency design", "level" : "intermediate" }, { "name" : "Event pipelines", "level" : "intermediate" }, { "name" : "Data integrity", "level" : "intermediate" }, { "name" : "Cache coherence", "level" : "intermediate" }, { "name" : "Exactly-once processing", "level" : "intermediate" }, { "name" : "Backpressure handling", "level" : "intermediate" }, { "name" : "Circuit breaking", "level" : "intermediate" }, { "name" : "Idempotent retry logic", "level" : "intermediate" }, { "name" : "Graceful degradation", "level" : "intermediate" }, { "name" : "Fan-out problem", "level" : "intermediate" }, { "name" : "Schema evolution", "level" : "intermediate" }, { "name" : "Testing practices", "level" : "intermediate" }, { "name" : "Deployment patterns", "level" : "intermediate" }, { "name" : "Production reliability", "level" : "intermediate" }, { "name" : "On-call triage", "level" : "intermediate" }, { "name" : "Durable fixes", "level" : "intermediate" }, { "name" : "Technical direction", "level" : "intermediate" }, { "name" : "Architectural decisions", "level" : "intermediate" }, { "name" : "Success metrics", "level" : "intermediate" }, { "name" : "Latency budgets", "level" : "intermediate" }, { "name" : "Throughput targets", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Leadership" }, { "name" : "Mentoring" } ], "majorSkills" : "Distributed systems, Event-driven infrastructure, High-throughput systems, Low-latency design", "majorSkillsList" : [ "Distributed systems", "Event-driven infrastructure", "High-throughput systems", "Low-latency design" ], "coreResponsibilities" : "Design distributed systems, Build distributed systems, Scale distributed systems, Architect for traffic spikes, Architect for concurrency, Own development event pipelines, Optimize event pipelines, Build low-latency data layers, Tune low-latency data layers, Implement resilience patterns, Enforce resilience patterns, Contribute user-facing systems, Solve fan-out problem, Partner with leadership, Align technical execution, Contribute build vs buy, Contribute platform strategy, Set engineering standards, Uphold engineering standards, Mentor junior engineers, Develop junior engineers, Raise technical floor", "teamCollaboration" : "Partner with product; Partner with engineering leadership; Code reviews; RFCs; Technical documentation; Pairing; Design reviews", "projectManagementSkills" : [ "Platform strategy" ], "domainKnowledge" : "Distributed systems; Real-money trading; High-throughput systems; Low-latency design; Event-driven infrastructure; Prediction markets; Sportsbook; iGaming platform; Financial platforms; Real-time trading; Cloud-native infrastructure", "domainList" : [ "distributed-systems", "real-money-trading", "high-throughput-systems", "low-latency-design", "event-driven-infrastructure", "prediction-markets", "sportsbook", "igaming-platform", "financial-platforms", "real-time-trading", "cloud-native-infrastructure" ], "domainSpecificKnowledge" : [ "Distributed systems", "Real-money trading", "High-throughput systems", "Low-latency design", "Event-driven infrastructure", "Prediction markets", "Sportsbook", "iGaming platform", "Financial platforms", "Real-time trading", "Cloud-native infrastructure" ], "toolProficiency" : [ "Spring Boot", "Kafka", "Postgres", "Redis", "Kubernetes", "Helm", "Terraform", "AWS" ], "documentationSkills" : "Technical documentation", "problemSolvingSkills" : "Root cause analysis; Troubleshooting; Diagnose bottlenecks", "specialRequirements" : "On-call", "outcomesObjectives" : "Hold systems accountable", "qualificationsBasic" : "5+ years software engineering, 5+ years distributed systems, 5+ years high-concurrency production, Expert Java or Kotlin, Expert Spring Boot, Command modern API design, Deep Kafka experience, Diagnose and resolve bottlenecks", "qualificationsPreferred" : "Experience real-time delivery systems, Familiarity financial platforms, Familiarity real-time trading, Familiarity prediction markets, Experience high-growth startup", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "About Us Fanatics is building a leading global digital sports platform. We ignite the passions of global sports fans and maximize the presence and reach for our hundreds of sports partners globally by offering products and services across Fanatics Commerce, Fanatics Collectibles, and Fanatics Betting collect physical and digital trading cards, sports memorabilia, and other digital assets; and bet as the company builds its Sportsbook and iGaming platform. Fanatics has an established database of over 100 million global sports fans; a global partner network with approximately 900 sports properties, including major national and international professional sports leagues, players associations, teams, colleges, college conferences and retail partners, 2,500 athletes and celebrities, and 200 exclusive athletes; and over 2,000 retail locations, including its Lids retail stores. Our more than 22,000 employees are committed to relentlessly enhancing the fan experience and delighting sports fans globally. About the Team Launched in 2021, Fanatics Betting and Gaming is the online and retail sports betting subsidiary of Fanatics, a global digital sports platform. The Fanatics Sportsbook is available to 95% of the addressable online sports bettor market in the U. S. Fanatics Casino is currently available online in Michigan, New Jersey, Pennsylvania and West Virginia. Fanatics Betting and Gaming operates twenty-two retail sports betting locations, including the only sportsbook inside an NFL stadium at Northwest Stadium. Fanatics Betting and Gaming is headquartered in New York with offices in Denver, Leeds and Dublin. Fanatics Markets is the real-money prediction and trading app where you can invest in moments you care about. Built on a secure platform, we let users predict real-world outcomes and trade on events they actually follow - from sports and entertainment to political elections and beyond. Our mission is to redefine how fans engage with the moments and markets that matter most. We're looking for the right people to help us build the future of prediction markets. The Opportunity As a Sr Software Engineer on our Distributed Systems team, you'll be at the core of what makes Fanatics Markets work — the event-driven infrastructure that powers real-money trading at scale. This is a role for an engineer who moves fluidly between hands-on coding and architectural influence: someone who can design a system that handles massive traffic spikes during live events, then roll up their sleeves and build it. You'll work alongside some of the most experienced distributed systems engineers in the industry, owning meaningful technical decisions and directly shaping how the platform scales over the next several years. If you thrive at the intersection of high-throughput systems, low-latency design, and technical leadership — this is your seat Responsibilities Design, build, and scale distributed systems using Kotlin, Java, and Spring Boot, architecting for the traffic spikes and concurrency demands of a live real-money trading platform. Own the development and optimization of high-throughput event pipelines using Kafka, including partition strategy, consumer group design, and exactly-once processing guarantees. Build and tune low-latency data layers across Postgres, Redis, and Redis PubSub — ensuring data integrity, cache coherence, and sub-millisecond read paths under peak load. Implement and enforce resilience patterns across services — backpressure handling, circuit breaking, idempotent retry logic, and graceful degradation under failure conditions. Contribute to real-time user-facing systems, solving the fan-out problem for live market updates across tens of thousands of concurrent sessions. Partner with product and engineering leadership to align technical execution with business priorities — contributing to build vs. buy decisions and long-term platform strategy. Set and uphold engineering standards for observability, schema evolution, testing practices, and deployment patterns across the team — through code reviews, RFCs, and technical documentation. Mentor and actively develop junior and mid-level engineers, raising the technical floor of the team through pairing, design reviews, and direct feedback. Qualifications 5+ years of software engineering experience with a primary focus on distributed systems and high-concurrency production environments. Expert-level proficiency in Java or Kotlin and Spring Boot, with a strong command of modern API design — REST, gRPC, and Protobuf. Deep hands-on experience with Kafka (or Redpanda/Pub Sub) — including internal mechanics, partition strategies, consumer group rebalancing, and delivery guarantees. Proven ability to diagnose and resolve bottlenecks in asynchronous messaging systems and implement patterns like idempotency, distributed caching, and exactly-once processing. Hands-on experience with Kubernetes, Helm, Terraform, and cloud-native infrastructure on AWS. Strong instincts for production reliability — you've been on-call, triaged distributed system failures under pressure, and shipped durable fixes. Demonstrated ability to influence technical direction across teams and guide engineers through complex architectural decisions without direct authority. Track record of defining success metrics upfront — SLAs, latency budgets, throughput targets — and holding systems accountable to them in production. Preferred Experience with real-time delivery systems — WebSocket fan-out, server-sent events, or pub/sub at scale. Familiarity with financial platforms, real-time trading systems, or prediction markets. Experience in a high-growth startup environment where ownership is broad and the technical landscape evolves quickly. Depending on the role, your interview and onboarding experience may include in-person components, such as onsite interviews or Launching into Better: LIVE—a multi-day cultural immersion in New York City for full-time, non-seasonal hires. These sessions are designed to build connection and bring our culture to life, though specific travel and participation requirements will be confirmed based on your role and location. Your recruiter will provide clear guidance at each stage of the process. For information about our benefits, please visit https://benefitsatfanatics.com/ #LI-Remote #LI-AL1 Ranges will change based on country and state of residence, which are reflected in Geographical Zones defined by Fanatics Betting and Gaming. The range incorporates all of our Geographical Compensation Zones and is subject to change as the Zone associated with the actual offer is confirmed. In addition to the base and bonus, full-time employment, and more. For information about our benefits, please visit https://benefitsatfanatics.com/ Salary Range $152,000—$200,000 USD By submitting your application, you agree to our terms of service and acknowledge you have read our Candidate Privacy Policy.", "summaryDescription" : "Senior Software Engineer - Distributed Systems at Fanatics Betting & Gaming. Skills: Distributed systems, Event-driven infrastructure, High-throughput systems, Low-latency design. Design distributed systems. Build distributed systems", "postedDate" : "2026-06-13T21:31:30.902", "createdAt" : "2026-06-13T21:31:30.902", "lastUpdated" : "2026-06-15T06:37:08.299", "ingestTimestamp" : "2026-06-13T21:31:30.902", "mongoId" : "6a2c95ab74d8ee00a098db03", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 152000, "salaryAnnualMax" : 200000, "salaryBand" : "150k-200k", "hasSalary" : true, "allSkills" : [ "Distributed systems", "High-throughput systems", "Low-latency design", "Event pipelines", "Data integrity", "Cache coherence", "Exactly-once processing", "Backpressure handling", "Circuit breaking", "Idempotent retry logic", "Graceful degradation", "Fan-out problem", "Schema evolution", "Testing practices", "Deployment patterns", "Production reliability", "On-call triage", "Durable fixes", "Technical direction", "Architectural decisions", "Success metrics", "Latency budgets", "Throughput targets", "Leadership", "Mentoring", "Event-driven infrastructure", "API design", "System design", "Platform strategy", "Technical leadership", "Build vs buy", "Real-money trading", "Prediction markets", "Sportsbook", "iGaming platform", "Financial platforms", "Real-time trading", "Cloud-native infrastructure", "Spring Boot", "Kafka", "Postgres", "Redis", "Kubernetes", "Helm", "Terraform", "AWS" ], "skillCount" : 46, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a305119f292fd229cef9d45", "title" : "Monitoring Product Marketing Manager", "industry" : "Marketing", "salary" : { "min" : 105600.0, "max" : 145200.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : false }, "location" : "US", "locations" : [ "US" ], "timestamp" : "2026-06-16T11:54:35.906", "fingerprint" : "e2ac9e28b1feb7af28ad1539a61f122b65844a442e3a5fb57db65566037e9261", "source" : "lever", "language" : "en", "applyUrl" : "https://jobs.lever.co/jobgether/71f3259b-7566-4a41-9d91-cb44a53f52e6/apply", "externalId" : "71f3259b-7566-4a41-9d91-cb44a53f52e6", "industryFunction" : { }, "structuredLocations" : [ { "country" : "United States", "continent" : "na", "workMode" : "remote" } ], "locationText" : "United States", "employmentType" : "FULL_TIME", "minimumEducation" : "Bachelor's", "experienceMinYears" : 3, "experienceLevel" : "Manager", "professionalSkills" : [ "Product marketing", "Product management", "Market analysis", "Go-to-market strategy", "Product messaging", "Brand awareness", "Market leadership", "Ecosystem development" ], "hardSkillsList" : [ "Geospatial technologies", "Geospatial applications", "Monitoring systems", "Surveying technologies" ], "hardSkills" : [ { "name" : "Geospatial technologies", "level" : "intermediate" }, { "name" : "Geospatial applications", "level" : "intermediate" }, { "name" : "Monitoring systems", "level" : "intermediate" }, { "name" : "Surveying technologies", "level" : "intermediate" } ], "majorSkills" : "Product marketing, Go-to-market strategy, Market analysis", "majorSkillsList" : [ "Product marketing", "Go-to-market strategy", "Market analysis" ], "coreResponsibilities" : "Define global product marketing strategy, Lead go-to-market strategy, Drive product lifecycle, Act as subject matter expert, Align engineering, product, sales teams, Conduct global field research, Conduct market analysis, Build compelling product messaging, Build compelling product positioning, Represent monitoring portfolio, Promote monitoring portfolio, Collaborate cross-functionally, Support strategic partnerships, Support ecosystem development", "teamCollaboration" : "Cross-functional teams; Engineering teams; Product teams; Sales teams; Global teams", "projectManagementSkills" : [ "Project management" ], "domainKnowledge" : "Construction industry; Infrastructure industry; Mining industry; Geospatial technologies; Monitoring systems; Surveying technologies", "domainList" : [ "construction-industry", "infrastructure-industry", "mining-industry", "geospatial-technologies", "monitoring-systems", "surveying-technologies" ], "domainSpecificKnowledge" : [ "Construction industry", "Infrastructure industry", "Mining industry", "Geospatial technologies", "Monitoring systems", "Surveying technologies" ], "communicationSkills" : "Simplify complex technical concepts", "continuousLearning" : "Continuous learning", "innovationCreativity" : "Innovation", "specialRequirements" : "Willingness to travel internationally 20-30%", "outcomesObjectives" : "Strengthen brand awareness; Expand product reach; Expand product adoption; Market leadership", "qualificationsBasic" : "Bachelor’s degree in STEM, 3+ years of experience in product marketing, Understanding of monitoring systems, Proven ability to influence cross-functional teams, Excellent communication skills, Organizational and project management skills, Demonstrated ownership mindset", "qualificationsPreferred" : "Experience with Jira, Experience with Miro, Experience with DOMO, Experience with Google Workspace", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "## Accountabilities Define and lead global product marketing and go-to-market strategy for monitoring solutions across construction, infrastructure, and mining sectors. Drive the full product lifecycle, from market requirements and positioning through launch execution and post-launch optimization. Act as a subject matter expert, aligning engineering, product, and sales teams around customer needs and strategic market opportunities. Conduct global field research and market analysis to identify gaps, emerging trends, and new business opportunities. Build and execute compelling product messaging and positioning that translates complex geospatial technologies into clear customer value. Represent and promote the monitoring portfolio at global industry events, conferences, and trade shows to strengthen brand awareness and market leadership. Collaborate cross-functionally to ensure alignment between product development priorities and market demand. Support strategic partnerships and ecosystem development to expand product reach and adoption. Requirements: Bachelor’s degree in a STEM field such as Geomatics, Civil Engineering, Geotechnical Engineering, Surveying, or a related discipline. 3+ years of experience in product marketing, product management, or a related technical commercial role within geospatial, construction, mining, or infrastructure industries. Strong understanding of monitoring systems, surveying technologies, or related geospatial applications. Proven ability to influence cross-functional teams and drive product strategy without formal authority. Excellent communication skills with the ability to simplify complex technical concepts for both technical and non-technical audiences. Strong organizational and project management skills with the ability to thrive in fast-paced, global environments. Demonstrated ownership mindset with accountability for product success and go-to-market execution. Experience with tools such as Jira, Miro, DOMO, or Google Workspace is a plus. Willingness to travel internationally approximately 20–30% of the time. Benefits: Competitive salary range approximately $105,600 to $145,200 annually, with eligibility for performance-based bonuses. Comprehensive health coverage including medical, dental, and vision insurance. Retirement savings plans and Employee Stock Purchase Plan. Paid time off, parental leave, and flexible work arrangements depending on location. Opportunity to work on cutting-edge geospatial and monitoring technologies with real-world global impact. International exposure through collaboration with global teams and industry events. Professional growth in a highly innovative, engineering-driven environment. Inclusive and collaborative culture focused on ownership, innovation, and continuous learning. ## Additional Information How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1", "summaryDescription" : "Monitoring Product Marketing Manager. Skills: Product marketing, Go-to-market strategy, Market analysis. Define global product marketing strategy. Lead go-to-market strategy", "postedDate" : "2026-06-15T08:21:46.896", "createdAt" : "2026-06-15T08:21:46.896", "lastUpdated" : "2026-06-16T11:54:35.906", "ingestTimestamp" : "2026-06-16T03:23:09.933", "mongoId" : "6a305119f292fd229cef9d45", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 105600, "salaryAnnualMax" : 145200, "salaryBand" : "100k-150k", "hasSalary" : true, "allSkills" : [ "Geospatial technologies", "Geospatial applications", "Monitoring systems", "Surveying technologies", "Product marketing", "Go-to-market strategy", "Market analysis", "Product management", "Product messaging", "Brand awareness", "Market leadership", "Ecosystem development", "Project management", "Construction industry", "Infrastructure industry", "Mining industry" ], "skillCount" : 16, "jobCategory" : "marketing", "jobSubcategory" : "growth", "seniorityLevel" : "Mid", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.97 }, { "id" : "6a305119f292fd229cef9d44", "title" : "Monitoring Product Marketing Manager", "industry" : "Marketing", "salary" : { "min" : 105600.0, "max" : 145200.0, "currency" : "CAD", "frequency" : "yearly", "is_estimated" : false }, "location" : "Canada", "locations" : [ "Canada" ], "timestamp" : "2026-06-16T11:04:02.703", "fingerprint" : "433f13b9dea8c235c194cb8c1cbc79a0f12f84a1589ee57da9b9afe89f5b0c2b", "source" : "lever", "language" : "en", "applyUrl" : "https://jobs.lever.co/jobgether/66d7dd5a-2f6c-4949-961e-8004ff6b4433/apply", "externalId" : "66d7dd5a-2f6c-4949-961e-8004ff6b4433", "industryFunction" : { }, "structuredLocations" : [ { "country" : "Canada", "continent" : "na", "workMode" : "onsite" } ], "locationText" : "Canada", "employmentType" : "FULL_TIME", "minimumEducation" : "Bachelor's", "experienceMinYears" : 3, "experienceLevel" : "Manager", "professionalSkills" : [ "Product strategy", "Market analysis", "Go-to-market strategy", "Product lifecycle management" ], "hardSkillsList" : [ "Geospatial technologies", "Product messaging", "Customer value proposition" ], "hardSkills" : [ { "name" : "Geospatial technologies", "level" : "intermediate" }, { "name" : "Product messaging", "level" : "intermediate" }, { "name" : "Customer value proposition", "level" : "intermediate" } ], "majorSkills" : "Product marketing, Go-to-market strategy, Market analysis", "majorSkillsList" : [ "Product marketing", "Go-to-market strategy", "Market analysis" ], "coreResponsibilities" : "Define global product marketing strategy, Lead go-to-market strategy, Drive product lifecycle, Act as subject matter expert, Align engineering, product, and sales, Conduct global field research, Conduct market analysis, Build compelling product messaging, Build product positioning, Represent monitoring portfolio, Promote monitoring portfolio, Collaborate cross-functionally, Ensure alignment between priorities and demand, Support strategic partnerships, Support ecosystem development", "teamCollaboration" : "Align engineering, product, sales; Cross-functional collaboration", "projectManagementSkills" : [ "Project management" ], "domainKnowledge" : "Construction industry; Infrastructure industry; Mining sectors; Monitoring systems; Surveying technologies; Geospatial applications", "domainList" : [ "construction-industry", "infrastructure-industry", "mining-sectors", "monitoring-systems", "surveying-technologies", "geospatial-applications" ], "domainSpecificKnowledge" : [ "Construction industry", "Infrastructure industry", "Mining sectors", "Monitoring systems", "Surveying technologies", "Geospatial applications" ], "communicationSkills" : "Simplify complex technical concepts", "specialRequirements" : "Willingness to travel internationally", "qualificationsBasic" : "Bachelor’s degree in STEM, 3+ years product marketing experience, Understanding of monitoring systems, Proven ability to influence cross-functional teams, Organizational and project management skills, Demonstrated ownership mindset", "qualificationsPreferred" : "Experience with Jira, Experience with Miro, Experience with DOMO, Experience with Google Workspace", "remoteFriendly" : true, "workSiteFlexibility" : "Flexible", "rawDescription" : "## Accountabilities Define and lead global product marketing and go-to-market strategy for monitoring solutions across construction, infrastructure, and mining sectors. Drive the full product lifecycle, from market requirements and positioning through launch execution and post-launch optimization. Act as a subject matter expert, aligning engineering, product, and sales teams around customer needs and strategic market opportunities. Conduct global field research and market analysis to identify gaps, emerging trends, and new business opportunities. Build and execute compelling product messaging and positioning that translates complex geospatial technologies into clear customer value. Represent and promote the monitoring portfolio at global industry events, conferences, and trade shows to strengthen brand awareness and market leadership. Collaborate cross-functionally to ensure alignment between product development priorities and market demand. Support strategic partnerships and ecosystem development to expand product reach and adoption. Requirements: Bachelor’s degree in a STEM field such as Geomatics, Civil Engineering, Geotechnical Engineering, Surveying, or a related discipline. 3+ years of experience in product marketing, product management, or a related technical commercial role within geospatial, construction, mining, or infrastructure industries. Strong understanding of monitoring systems, surveying technologies, or related geospatial applications. Proven ability to influence cross-functional teams and drive product strategy without formal authority. Excellent communication skills with the ability to simplify complex technical concepts for both technical and non-technical audiences. Strong organizational and project management skills with the ability to thrive in fast-paced, global environments. Demonstrated ownership mindset with accountability for product success and go-to-market execution. Experience with tools such as Jira, Miro, DOMO, or Google Workspace is a plus. Willingness to travel internationally approximately 20–30% of the time. Benefits: Competitive salary range approximately $105,600 to $145,200 annually, with eligibility for performance-based bonuses. Comprehensive health coverage including medical, dental, and vision insurance. Retirement savings plans and Employee Stock Purchase Plan. Paid time off, parental leave, and flexible work arrangements depending on location. Opportunity to work on cutting-edge geospatial and monitoring technologies with real-world global impact. International exposure through collaboration with global teams and industry events. Professional growth in a highly innovative, engineering-driven environment. Inclusive and collaborative culture focused on ownership, innovation, and continuous learning. ## Additional Information How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1", "summaryDescription" : "Monitoring Product Marketing Manager. Skills: Product marketing, Go-to-market strategy, Market analysis. Define global product marketing strategy. Lead go-to-market strategy", "postedDate" : "2026-06-15T08:21:14.630", "createdAt" : "2026-06-15T08:21:14.630", "lastUpdated" : "2026-06-16T11:04:02.703", "ingestTimestamp" : "2026-06-16T03:24:35.656", "mongoId" : "6a305119f292fd229cef9d44", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "100k-150k", "hasSalary" : false, "allSkills" : [ "Geospatial technologies", "Product messaging", "Customer value proposition", "Product marketing", "Go-to-market strategy", "Market analysis", "Product strategy", "Product lifecycle management", "Project management", "Construction industry", "Infrastructure industry", "Mining sectors", "Monitoring systems", "Surveying technologies", "Geospatial applications" ], "skillCount" : 15, "jobCategory" : "marketing", "jobSubcategory" : "growth", "seniorityLevel" : "Mid", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.97 }, { "id" : "6a2c9fa174d8ee00a09a02ac", "title" : "Distributed Training and Inference Engineer", "company" : "Sciforium", "industry" : "Engineering", "salary" : { "min" : 190000.0, "max" : 250000.0, "currency" : "USD", "frequency" : "Yearly" }, "location" : "San Francisco", "locations" : [ "San Francisco" ], "timestamp" : "2026-06-15T06:24:58.002", "fingerprint" : "de62a9b003de0a24b72103a3209e8e6725e57688b89a757691547cc43a0ea620", "source" : "ashby", "language" : "en", "applyUrl" : "https://jobs.ashbyhq.com/sciforium/1471adc1-cf58-4174-8dc2-e8c0e29cfb17/application", "externalId" : "1471adc1-cf58-4174-8dc2-e8c0e29cfb17", "industryFunction" : { }, "structuredLocations" : [ { "city" : "San Francisco", "state" : "California", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "37.7879363,-122.4075201" } ], "locationText" : "San Francisco, California, United States", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Python, C++, JAX, PyTorch, CUDA, ROCm, NCCL, XLA", "professionalSkills" : [ "Systems engineering", "Performance optimization", "Systems integration", "Debugging complex issues" ], "hardSkillsList" : [ "Distributed training", "ML systems", "ML infrastructure", "Large-scale AI training", "Large-scale AI serving", "Multi-node distributed training", "Partitioning configuration" ], "hardSkills" : [ { "name" : "Distributed training", "level" : "intermediate" }, { "name" : "ML systems", "level" : "intermediate" }, { "name" : "ML infrastructure", "level" : "intermediate" }, { "name" : "Large-scale AI training", "level" : "intermediate" }, { "name" : "Large-scale AI serving", "level" : "intermediate" }, { "name" : "Multi-node distributed training", "level" : "intermediate" }, { "name" : "Partitioning configuration", "level" : "intermediate" } ], "majorSkills" : "Distributed training, ML infrastructure, Systems engineering, Performance optimization", "majorSkillsList" : [ "Distributed training", "ML infrastructure", "Systems engineering", "Performance optimization" ], "coreResponsibilities" : "Maintain ML libraries, Update ML frameworks, Optimize ML libraries, Optimize ML frameworks, Build ML software stack, Maintain ML software stack, Improve ML software stack, Shard model implementations, Partition model implementations, Configure model implementations, Integrate modules, Validate modules, Profile compilation graphs, Profile training workloads, Profile runtime execution, Eliminate performance bottlenecks, Troubleshoot hardware-software issues, Collaborate with research teams, Collaborate with infrastructure teams, Collaborate with kernel engineering teams, Improve system throughput, Improve system stability, Improve developer experience", "teamCollaboration" : "Collaborate with research; Collaborate with infrastructure; Collaborate with kernel engineering", "domainKnowledge" : "Multimodal AI models; AI serving platform; Frontier AI models; Real-time applications; LLMs; Generative AI models; ML stack; CUDA runtimes; ROCm runtimes; Distributed systems; GPU clusters; Accelerator clusters; ML frameworks; Compilation internals; Custom lowering paths; Large-scale inference", "domainList" : [ "multimodal-ai-models", "ai-serving-platform", "frontier-ai-models", "real-time-applications", "llms", "generative-ai-models", "ml-stack", "cuda-runtimes", "rocm-runtimes", "distributed-systems", "gpu-clusters", "accelerator-clusters", "ml-frameworks", "compilation-internals", "custom-lowering-paths", "large-scale-inference" ], "domainSpecificKnowledge" : [ "Multimodal AI models", "AI serving platform", "Frontier AI models", "Real-time applications", "LLMs", "Generative AI models", "ML stack", "CUDA runtimes", "ROCm runtimes", "Distributed systems", "GPU clusters", "Accelerator clusters", "ML frameworks", "Compilation internals", "Custom lowering paths", "Large-scale inference" ], "toolProficiency" : [ "Nsight", "ROCm Profiler", "XLA profiler", "TPU tools", "VLLM", "TensorRT", "FasterTransformer" ], "problemSolvingSkills" : "Debugging complex issues; Troubleshooting; Performance analysis", "qualificationsBasic" : "5+ years industry experience, Bachelor's or Master's degree, Python, C++ programming, ML tooling familiarity, Distributed systems familiarity", "qualificationsPreferred" : "Extensive XLA/JAX stack experience, Familiarity with distributed serving, Familiarity with large-scale inference, GPU kernel optimization background, Accelerator-aware model partitioning background", "rawDescription" : "Sciforium is an AI infrastructure company developing next-generation multimodal AI models and a proprietary, high-efficiency serving platform. Backed by multi-million-dollar funding and direct sponsorship from AMD with hands-on support from AMD engineers the team is scaling rapidly to build the full stack powering frontier AI models and real-time applications. ABOUT THE ROLE Sciforium is seeking a highly skilled Distributed Training and Inference Engineer to build, optimize, and maintain the critical software stack that powers our large-scale AI training and serving workloads. In this role, you will work across the entire machine learning infrastructure from low-level CUDA/ROCm runtimes to high-level frameworks like JAX and PyTorch to ensure our distributed training systems are fast, scalable, stable, and efficient. This position is ideal for someone who loves deep systems engineering, debugging complex hardware–software interactions, and optimizing performance at every layer of the ML stack. You will play a pivotal role in enabling the training and deployment of next-generation LLMs and generative AI models. WHAT YOU'LL DO - Software Stack Maintenance: Maintain, update, and optimize critical ML libraries and frameworks including JAX, PyTorch, CUDA, and ROCm across multiple environments and hardware configurations. - End-to-End Stack Ownership: Build, maintain, and continuously improve the entire ML software stack from ROCm/CUDA drivers to high-level JAX/PyTorch tooling. - Distributed System Optimization: Ensure all model implementations are efficiently sharded, partitioned, and configured for large-scale distributed training and serving. - System Integration: Continuously integrate and validate modules for runtime correctness, memory efficiency, and scalability across multi-node GPU/accelerator clusters. - Profiling & Performance Analysis: Conduct detailed profiling of compilation graphs, training workloads, and runtime execution to optimize performance and eliminate bottlenecks. - Debugging & Reliability: Troubleshoot complex hardware–software interaction issues, including vLLM compilation failures on ROCm, CUDA memory leaks, distributed runtime failures, and kernel-level inconsistencies. - Collaborate with research, infrastructure, and kernel engineering teams to improve system throughput, stability, and developer experience. IDEAL CANDIDATE PROFILE - 5+ years of industry experience in ML systems, distributed training, or related fields. - Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or related technical fields. - Strong programming experience in Python, C++, and familiarity with ML tooling and distributed systems. - Deep understanding of profiling tools (e.g., Nsight, ROCm Profiler, XLA profiler, TPU tools). - Deep expertise with partitioning configuration on the modern ML frameworks such as PyTorch and JAX. - Experience with multi-node distributed training systems and orchestration frameworks (DTensor, GSPMD, etc.). - Hands-on experience maintaining or building ML training stacks involving CUDA, ROCm, NCCL, XLA, or similar technologies. NICE-TO-HAVE - Extensive experience with the XLA/JAX stack, including compilation internals and custom lowering paths. - Familiarity with distributed serving or large-scale inference frameworks (e.g., vLLM, TensorRT, FasterTransformer). - Background in GPU kernel optimization or accelerator-aware model partitioning. - Strong understanding of low-level C++ building blocks used in ML frameworks (e.g., XLA, CUDA kernels, custom ops). BENEFITS INCLUDE - Medical, dental, and vision insurance - 401k plan - Daily lunch, snacks, and beverages - Flexible time off - Competitive salary and equity EQUAL OPPORTUNITY Sciforium is an equal opportunity employer. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status.", "summaryDescription" : "Distributed Training and Inference Engineer at Sciforium. Skills: Distributed training, ML infrastructure, Systems engineering, Performance optimization. Maintain ML libraries. Update ML frameworks", "createdAt" : "2026-06-13T22:18:10.252", "lastUpdated" : "2026-06-15T06:24:58.002", "ingestTimestamp" : "2026-06-13T22:18:10.252", "mongoId" : "6a2c9fa174d8ee00a09a02ac", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 190000, "salaryAnnualMax" : 250000, "salaryBand" : "150k-200k", "hasSalary" : true, "allSkills" : [ "Distributed training", "ML systems", "ML infrastructure", "Large-scale AI training", "Large-scale AI serving", "Multi-node distributed training", "Partitioning configuration", "Systems engineering", "Performance optimization", "Systems integration", "Debugging complex issues", "Multimodal AI models", "AI serving platform", "Frontier AI models", "Real-time applications", "LLMs", "Generative AI models", "ML stack", "CUDA runtimes", "ROCm runtimes", "Distributed systems", "GPU clusters", "Accelerator clusters", "ML frameworks", "Compilation internals", "Custom lowering paths", "Large-scale inference", "Nsight", "ROCm Profiler", "XLA profiler", "TPU tools", "VLLM", "TensorRT", "FasterTransformer" ], "skillCount" : 34, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 0.8888889, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2ca58f74d8ee00a09b7151", "title" : "Senior Manager, Engineering - Observability Platform", "company" : "Smartsheet", "industry" : "SaaS", "salary" : { "min" : 205000.0, "max" : 275000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : false }, "location" : "United States", "locations" : [ "United States" ], "timestamp" : "2026-06-16T04:21:23.690", "fingerprint" : "099e83e5bcfe33e7e43ce143089ab3c4aa31975fa8b515a2a54ae8f7e53b5a84", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.greenhouse.io/smartsheet/jobs/8003557", "externalId" : "8003557", "industryFunction" : { }, "structuredLocations" : [ { "country" : "United States", "continent" : "na", "workMode" : "remote" } ], "locationText" : "United States", "employmentType" : "FULL_TIME", "experienceLevel" : "Manager", "remoteFriendly" : true, "workSiteFlexibility" : "Flexible", "rawDescription" : "For over 20 years, Smartsheet has empowered teams to manage work seamlessly and scale solutions smarter. Now, in our most ambitious chapter yet, we are uniting human teams with AI agents. By orchestrating the work agents do best, automating manual tasks and uncovering insights at scale, we create the space for people to focus on what truly matters: judgment, creativity, and big thinking. That is magic at work, and it’s what we show up for every day. The Observability Platform team is seeking a Senior Manager of Engineering to build and lead a centralized platform capability that gives Smartsheet full-stack visibility into our most complex and consequential systems. This role owns the engineering strategy and execution for a dedicated platform consolidating multiple platforms, serving engineering teams across the company, including the Data & AI Platform, Commerce, and Infrastructure pillars. You will lead a team based with strategic ownership spanning metrics, distributed tracing, alerting, log analytics, SLO/SLA management, and AI/ML observability integrations tied to SmartAssist and our agentic AI workstreams on Amazon Bedrock and MLflow. This is a high-leverage, high-visibility role at the intersection of platform reliability and AI-native engineering. You Will: Team & Platform Leadership Lead a team of engineers focused on observability platform engineering, driving build-out of a unified observability stack used by all engineering teams at Smartsheet. Own and evolve the platform's technical roadmap, consolidating multiple tooling platforms, and AI observability tooling into a coherent, scalable capability. Define platform standards, contribute to architectural direction, and ensure the team operates with engineering rigor and strong operational habits. Build and scale the team, hiring senior engineers and establishing effective global practices across distributed stakeholders. Observability Engineering Lead design and delivery of centralized observability infrastructure covering metrics pipelines, distributed tracing, alerting frameworks, and log analytics across Smartsheet services. Drive SLO/SLA definition and tooling for platform-wide reliability visibility, partnering closely with infrastructure, platform engineering, and on-call teams. Own governance including instrumentation standards, cost optimization, and rollout of advanced capabilities such as APM, RUM, and custom dashboards. Lead architecture, scaling, and operational practices for log analytics across high-throughput production workloads. Establish shared observability libraries, agents, and SDKs that reduce instrumentation burden for application engineering teams. AI Observability Build and maintain AI/ML observability integrations in partnership with the AI Platform team. Partner with the Data & AI Platform team to integrate MLflow tracing, Inference Tables, and LLM-as-judge evaluation pipelines into the observability stack. Develop dashboards and alerting for agentic AI workloads, including latency, token consumption, error rates, and evaluation metric drift. Contribute to the AI governance and cost observability program, providing telemetry for model usage, cost attribution, and compliance reporting. Cross-Functional Partnership & Execution Serve as the primary engineering partner for platform consumers across Data & AI, Commerce, Infrastructure, and Security teams, ensuring observability needs are met across workstreams. Lead complex, cross-functional observability projects with high ambiguity, managing delivery risk, communicating clearly to senior stakeholders, and building alignment across teams. Partner with delivery partners to coordinate instrumentation across platform modernization and migration workstreams Contribute to quarterly and annual platform goals, reporting on key reliability and observability metrics to engineering leadership. Communicate platform status, risks, and roadmap progress to Engineering leadership and above audiences in a clear, executive-ready format. Operational Excellence Embed on-call culture and incident management discipline into the team, ensuring clear runbooks, fast MTTR, and post-incident learning loops. Drive cost governance for observability tooling, including spend optimization and efficient resource management. Champion AI-assisted engineering practices within the team, applying tooling and automation to reduce toil and accelerate delivery. You Have: Required 10+ years of software or platform engineering experience, with strong fundamentals in distributed systems, infrastructure, and backend services. 3 years of engineering management experience, including direct team building, performance management, and cross-functional delivery ownership. Deep hands-on expertise with observability tooling: Datadog (APM, metrics, logs, alerting), OpenSearch or Elasticsearch, distributed tracing (OpenTelemetry or equivalent), and SLO/SLA management at scale. Proven experience operating observability platforms for high-availability, high-throughput production environments. Experience building and scaling engineering teams in distributed or international focus Strong execution track record on complex, cross-functional infrastructure programs with high ambiguity. Clear, direct communication (written and verbal) with both technical and non-technical audiences, including leadership and executive stakeholders. Proactive risk identification and status communication without prompting. Experience managing vendors, external delivery partners, and third-party integrations in a platform context. Preferred Hands-on experience with AI/ML observability: MLflow tracing, LLM evaluation pipelines, or observability for agentic AI systems. Familiarity with Amazon Bedrock, ECS Fargate, or LangGraph-based multi-agent architectures. Experience with cloud cost governance and FinOps practices for observability tooling Exposure to data platform observability and data quality monitoring in a lakehouse context Experience establishing internal developer platforms, shared libraries, or platform-as-a-service offerings for application teams. Prior work in SaaS environments with enterprise compliance requirements (SOC 2, FedRAMP, HIPAA). Education & Eligibility CS, Engineering, or equivalent degree, or commensurate practical experience. Legally eligible to work in the U. S. on an ongoing basis Current US Perks & Benefits: Employer subsidized medical/vision and dental coverage for full-time employees 401k Match to help you save for your future (50% of your contribution up to the first 6% of your eligible pay) Monthly stipend to support your work and productivity Flexible Time Away Program, plus Sick Time Off US employees are automatically covered under Smartsheet-sponsored life insurance, short-term, and long-term disability plans US employees receive 12 paid holidays per year Up to 24 weeks of Parental Leave Personal paid Volunteer Day to support our community Opportunities for professional growth and development including access to Udemy online courses Company Funded Perks, including a counseling membership, local retail discounts, and your own personal Smartsheet account Teleworking options from any registered location in the U. S. (role specific) Smartsheet provides a competitive base salary range for roles that may be hired in different geographic areas we are licensed to operate our business from. Actual compensation is determined by several factors including, but not limited to, level of professional, educational experience, skills, and specific candidate location. In addition, this role will be eligible for a market competitive incentive opportunity. US Base Salary Pay Range $205,000—$275,000 USD Get to Know Us: At Smartsheet, your ideas are heard, your potential is supported, and your contributions have real impact. You’ll have the freedom to explore, push boundaries, and grow beyond your role. We welcome diverse perspectives and nontraditional paths—because we know that impact comes from individuals who care deeply and challenge thoughtfully. When you’re doing work that stretches you, excites you, and connects you to something bigger, that’s magic at work. Let’s build what’s next, together. Equal Opportunity Employer: Smartsheet is an Equal Opportunity (EEO) employer committed to fostering an inclusive environment with the best employees. It is our policy to provide equal employment opportunities to all qualified applicants in accordance with applicable laws in the US, UK, Australia, Germany, Costa Rica, Japan, Bulgaria, and India. All qualified applicants will receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, protected veteran or disabled status, or genetic information. If there are preparations we can make to help ensure you have a comfortable and positive interview experience, please let us know. #LI-Remote", "summaryDescription" : "Senior Manager, Engineering - Observability Platform at Smartsheet", "postedDate" : "2026-06-14T19:20:23.146", "createdAt" : "2026-06-14T19:20:23.146", "lastUpdated" : "2026-06-16T04:21:23.690", "ingestTimestamp" : "2026-06-14T19:20:23.146", "mongoId" : "6a2ca58f74d8ee00a09b7151", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 205000, "salaryAnnualMax" : 275000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Manager", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2c8c8374d8ee00a0975b46", "title" : "Research Program Manager, Distributed Research", "company" : "WHOOP", "industry" : "Machine Learning & Research", "salary" : { "min" : 90000.0, "max" : 130000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : false }, "location" : "Boston, MA", "locations" : [ "Boston, MA" ], "timestamp" : "2026-06-15T05:22:33.973", "fingerprint" : "d7875d94140711e413684236beb88f118c7a2c72f00e387e843a75691cb75070", "source" : "ashby", "language" : "en", "applyUrl" : "https://jobs.ashbyhq.com/whoop/2f311632-71ef-4d53-b884-062e6ed1cfe3/application", "externalId" : "2f311632-71ef-4d53-b884-062e6ed1cfe3", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Boston", "state" : "Massachusetts", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "42.3588336,-71.0578303" } ], "locationText" : "Boston, Massachusetts, United States", "employmentType" : "FULL_TIME", "experienceMinYears" : 3, "experienceLevel" : "Manager", "technicalSkills" : "Jira, Agile methodologies", "professionalSkills" : [ "Process management", "Cross-functional coordination", "Vendor management", "Stakeholder management", "Resource planning", "Continuous improvement", "Intake processes", "Scoping processes", "Requirements definition", "Feasibility assessment", "Timing assessment", "Scope assessment", "Regulatory timelines", "Compliance timelines", "IRB review", "IRB approval", "Prioritization", "Trade-offs", "Execution plans", "Repeatable research execution", "Risk identification", "Risk mitigation", "System usage", "Dependency surfacing", "Prioritization frameworks", "Process optimization", "Efficiency increase", "Impact increase" ], "hardSkillsList" : [ "Operational metrics", "Data collection planning", "Data collection operations", "Distributed research efforts" ], "hardSkills" : [ { "name" : "Operational metrics", "level" : "intermediate" }, { "name" : "Data collection planning", "level" : "intermediate" }, { "name" : "Data collection operations", "level" : "intermediate" }, { "name" : "Distributed research efforts", "level" : "intermediate" } ], "majorSkills" : "Program management, Roadmap planning, Process scaling, Stakeholder alignment", "majorSkillsList" : [ "Program management", "Roadmap planning", "Process scaling", "Stakeholder alignment" ], "coreResponsibilities" : "Own program roadmap, Maintain program roadmap, Partner with researchers, Partner with stakeholders, Align priorities, Balance team capacity, Establish timelines, Lead intake processes, Lead scoping processes, Define requirements, Assess feasibility, Determine timing, Determine scope, Ensure planning incorporates timelines, Manage incoming requests, Prioritize incoming requests, Make trade-offs, Build intake workflows, Build SOPs, Build tracking systems, Build operational processes, Support research execution, Plan data collection initiatives, Execute data collection initiatives, Identify risks, Drive mitigation strategies, Own internal tooling, Manage internal tooling, Partner with technical teams, Enable system usage, Monitor system usage, Improve system usage, Collaborate cross-functionally, Align priorities, Surface dependencies, Support execution, Use program metrics, Use operational insights, Use performance indicators, Improve prioritization frameworks, Optimize processes, Increase efficiency, Increase impact", "teamCollaboration" : "Cross-functionally with Research; Cross-functionally with Product; Cross-functionally with Engineering; Cross-functionally with Operations; With researchers; With stakeholders; With technical teams", "projectManagementSkills" : [ "Program management", "Roadmap planning", "Intake processes", "Scoping processes", "Prioritization", "Execution", "Agile methodologies", "Workflow management" ], "domainKnowledge" : "Human subjects research; Decentralized research; Data collection infrastructure; AI tools", "domainList" : [ "human-subjects-research", "decentralized-research", "data-collection-infrastructure", "ai-tools" ], "domainSpecificKnowledge" : [ "Human subjects research", "Decentralized research", "Data collection infrastructure", "AI tools" ], "toolProficiency" : [ "Jira", "Workflow management systems" ], "communicationSkills" : "Stakeholder management", "documentationSkills" : "SOPs", "problemSolvingSkills" : "Analytical skills; Operational skills; Data-driven decision-making", "outcomesObjectives" : "Increase efficiency; Increase impact", "qualificationsBasic" : "3+ years Program Management, 3+ years Project Management, Manage intake, Manage prioritization, Manage roadmap planning, Manage execution, Build operational processes, Scale operational processes, Build workflows, Scale workflows, Build SOPs, Scale SOPs, Work with technical teams, Manage dependencies", "qualificationsPreferred" : "Research environment experience, Technical product experience, Data environment experience, Operations-focused experience, Experience supporting human subjects research, Experience supporting decentralized research operations, Experience supporting data collection infrastructure", "workSiteFlexibility" : "Onsite", "rawDescription" : "WHOOP is on a mission to unlock human performance and healthspan. This role sits at the center of that mission, ensuring our executives operate at maximum leverage. You will go beyond traditional administrative support by building systems, using AI tools, and proactively driving execution across priorities. RESPONSIBILITIES: - - Own and maintain the program roadmap for decentralized data collection initiatives, partnering with researchers and stakeholders to align priorities, balance team capacity, and establish realistic timelines - Lead intake and scoping processes for new requests by partnering with researchers and stakeholders to define requirements, assess feasibility, and determine appropriate timing and scope - Ensure decentralized data collection planning incorporates applicable regulatory and compliance timelines, including IRB review and approval milestones where applicable - Manage and prioritize incoming requests with a clear understanding of team bandwidth and operational constraints, making thoughtful trade-offs across scope, timing, and prioritization - Build and maintain scalable intake workflows, SOPs, tracking systems, and operational processes that support efficient and repeatable research execution - Ensure data collection initiatives are planned and executed without overextending technical systems or operational capacity, proactively identifying risks and driving mitigation strategies - Own and manage internal tooling that supports decentralized data collection operations, partnering closely with technical teams to enable, monitor, and improve system usage - Collaborate cross-functionally with Research, Product, Engineering, and Operations teams to align priorities, surface dependencies early, and support smooth execution across initiatives - Use program metrics, operational insights, and performance indicators to improve prioritization frameworks, optimize processes, and increase the overall efficiency and impact of distributed research efforts QUALIFICATIONS: - - 3+ years of experience in a Program Management or Project Management role, preferably within a research, technical product, data, or operations-focused environment - Demonstrated experience managing intake, prioritization, roadmap planning, and execution across multiple stakeholders and competing priorities - Proven ability to translate ambiguous or evolving requests into clearly defined scope, timelines, and actionable execution plans - Experience building and scaling operational processes, workflows, and SOPs in fast-paced, evolving environments - Familiarity with Agile methodologies and project management tools such as Jira or similar workflow management systems - Comfort working closely with technical teams and managing dependencies involving internal tooling, data systems, or operational infrastructure - Strong analytical, operational, and data-driven decision-making skills - Excellent communication, organizational, and stakeholder management skills with the ability to drive alignment across cross-functional teams - Experience supporting human subjects research, decentralized research operations, or data collection infrastructure is a plus - Passion for health, wellness, and WHOOP’s mission to unlock human performance and healthspan - Strong commitment to embracing and leveraging AI tools in day-to-day tasks, ensuring AI-assisted work aligns with the same high-quality standards as personal contributions. This role is based in the WHOOP office located in Boston, MA. The successful candidate must be prepared to relocate if necessary to work out of the Boston, MA office. Interested in the role, but don’t meet every qualification? We encourage you to still apply! At WHOOP, we believe there is much more to a candidate than what is written on paper, and we value character as much as experience. As we continue to build a diverse and inclusive environment, we encourage anyone who is interested in this role to apply. WHOOP is an Equal Opportunity Employer and participates in E-verify https://www.e-verify.gov/ to determine employment eligibility. It is unlawful in Massachusetts to require or administer a lie detector test as a condition of employment or continued employment. An employer who violates this law shall be subject to criminal penalties and civil liability. The WHOOP compensation philosophy is designed to attract, motivate, and retain exceptional talent by offering competitive base salaries, meaningful equity, and consistent pay practices that reflect our mission and core values. At WHOOP, we view total compensation as the combination of base salary, equity, and benefits, with equity serving as a key differentiator that aligns our employees with the long-term success of the company and allows every member of our corporate team to own part of WHOOP and share in the company’s long-term growth and success. The U.S. base salary range for this full-time position is $90,000 - $130,000. Salary ranges are determined by role, level, and location. Within each range, individual pay is based on factors such as job-related skills, experience, performance, and relevant education or training. In addition to the base salary, the successful candidate will also receive benefits and a generous equity package. These ranges may be modified in the future to reflect evolving market conditions and organizational needs. While most offers will typically fall toward the starting point of the range, total compensation will depend on the candidate’s specific qualifications, expertise, and alignment with the role’s requirements. ", "summaryDescription" : "Research Program Manager, Distributed Research at WHOOP. Skills: Program management, Roadmap planning, Process scaling, Stakeholder alignment. Own program roadmap. Maintain program roadmap", "createdAt" : "2026-06-13T22:10:22.370", "lastUpdated" : "2026-06-15T05:22:33.973", "ingestTimestamp" : "2026-06-13T22:10:22.370", "mongoId" : "6a2c8c8374d8ee00a0975b46", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 90000, "salaryAnnualMax" : 130000, "salaryBand" : "75k-100k", "hasSalary" : true, "allSkills" : [ "Operational metrics", "Data collection planning", "Data collection operations", "Distributed research efforts", "Program management", "Roadmap planning", "Process scaling", "Stakeholder alignment", "Process management", "Cross-functional coordination", "Vendor management", "Stakeholder management", "Resource planning", "Continuous improvement", "Intake processes", "Scoping processes", "Requirements definition", "Feasibility assessment", "Timing assessment", "Scope assessment", "Regulatory timelines", "Compliance timelines", "IRB review", "IRB approval", "Prioritization", "Trade-offs", "Execution plans", "Repeatable research execution", "Risk identification", "Risk mitigation", "System usage", "Dependency surfacing", "Prioritization frameworks", "Process optimization", "Efficiency increase", "Impact increase", "Execution", "Agile methodologies", "Workflow management", "Human subjects research", "Decentralized research", "Data collection infrastructure", "AI tools", "Jira", "Workflow management systems" ], "skillCount" : 45, "jobCategory" : "operations", "jobSubcategory" : "general", "seniorityLevel" : "Mid", "dataQualityScore" : 0.8888889, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a2d351e74d8ee00a0b16891", "title" : "Staff Product Manager, Agent Observability", "company" : "LiveKit", "industry" : "R&D", "salary" : { "min" : 225000.0, "max" : 265000.0, "currency" : "USD", "frequency" : "Yearly" }, "location" : "Hybrid, San Francisco", "locations" : [ "Hybrid, San Francisco" ], "timestamp" : "2026-06-16T04:41:40.341", "fingerprint" : "3d81f867511af7b87bc691a9565e5e6faddd396c2d242c7f65709a983972cb33", "source" : "ashby", "language" : "en", "applyUrl" : "https://jobs.ashbyhq.com/LiveKit/dc2e64b8-15fd-4d88-b2dd-c3106f76df4d/application", "externalId" : "dc2e64b8-15fd-4d88-b2dd-c3106f76df4d", "industryFunction" : { }, "structuredLocations" : [ { "city" : "San Francisco", "state" : "California", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "hybrid", "geo" : "37.7879363,-122.4075201" } ], "locationText" : "San Francisco, California, United States", "employmentType" : "FULL_TIME", "experienceLevel" : "Manager", "coreResponsibilities" : "Define product strategy, Develop product roadmap, Write user stories, Collaborate with engineering teams, Collaborate with design teams, Collaborate with marketing teams, Collaborate with sales teams, Gather customer feedback, Analyze market trends, Prioritize product backlog", "teamCollaboration" : "Cross-functional teams; Engineering; Design; Marketing; Sales", "projectManagementSkills" : [ "Roadmap planning" ], "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "ABOUT LIVEKIT LiveKit is building the infrastructure layer for the agentic era of computing. Our platform gives developers everything they need to build, test, deploy, scale, and observe AI agents in production. Founded in 2021, LiveKit powers voice and agentic AI applications for OpenAI, Salesforce, Spotify, Meta, and tens of thousands of other developers, collectively facilitating billions of calls each year. ABOUT THIS ROLE We're looking for a Product Manager to own LiveKit's Agent Observability product: how teams understand, debug, and trust what their voice agents do in production. Our PM team is small and high-leverage, with each PM coming in to establish the foundations in a new area of the business. Observability is one of the most important new products at LiveKit. It's central to our strategy, a surface of huge value to customers, and a category still in its infancy. You'd own it as the sole PM. You'll set the vision and roadmap for the whole observability suite, from traces and recordings to dashboards, evals, and quality metrics, and partner closely with the engineering team that builds it. The product has to serve two very different users at once: the engineer debugging why a call went wrong, and the non-technical operator reviewing quality, cost, and agent behavior. That makes it as hard at the UX layer as it is under the hood. The category for voice AI observability is being defined right now, and you'll be shaping a product used by some of the largest companies deploying voice agents at scale. YOU'LL THRIVE AT LIVEKIT IF YOU: - are obsessed with making the best product for our customers - are known as the go-to person for tackling tough problems - work hard and can build and ship fast - are focused on polish, detail, and quality - are a fast learner, frequently picking up new tips, tricks, and skills The best way to impress us is by trying LiveKit’s product, understanding the space, and bringing smart thoughts and opinions to the table. WHAT YOU'LL DO - Own the observability roadmap. Set a clear vision and a sequenced plan for the suite, and decide what gets built and when, in partnership with engineering. - Ship products people rely on. Turn a complex, data-dense problem into experiences customers use every day, and keep raising the bar on quality. - Make agent quality measurable. Build the evals and metrics teams need to know whether their agents are actually good and getting better, from latency and cost to conversation quality and behavior. - Design for two audiences at once. Make the product work for deeply technical users and non-technical operators without compromising either. - Get deep with customers and data. Understand how teams actually run and debug agents in production, and let that shape priorities. - Grow it into a business. Drive adoption and revenue so our observability revenue reflects the real value it delivers to customers. WHO YOU ARE - 8+ years in product management, at a senior or staff level, ideally having owned a developer-facing or data-heavy product. - Technical depth. You can reason about how a complex system works under the hood and earn the trust of strong engineers. You don't need to write code, but you need to understand systems well enough to make good tradeoffs. - Multi-persona product sense. You've built for both deeply technical users and non-technical ones in the same product, and have the design judgment to make dense, data-rich interfaces genuinely useful. - Cross-functional influence. LiveKit's engineering teams operate with high autonomy. You influence through clarity, trust, and good judgment, not process or hierarchy. - Communication as a superpower. You write clearly, present well, and can move between a board-level strategy conversation and a detailed technical discussion with an engineering lead. - Comfort with ambiguity. We're a small product team at a fast-growing company. You'll figure out what matters, prioritize ruthlessly, and move quickly without perfect information. NICE TO HAVE - Built an observability, monitoring, or analytics product, or a tool for evaluating and improving AI/LLM quality - Familiarity with evals, tracing, or quality measurement for AI/LLM or agent systems - Familiarity with how teams debug and monitor software in production (logs, traces, metrics, dashboards) - Background at a developer tools or infrastructure company - Familiarity with voice AI, real-time communication, or telephony - Experience with usage-based pricing models OUR COMMITMENT TO YOU - An opportunity to build something truly impactful to the world - Contribute to open source alongside world-class engineers - Competitive salary and equity package - Health, dental, and vision benefits - Flexible vacation policy LiveKit is an equal opportunity employer and does not discriminate on the basis of any characteristic protected by applicable law. If you require a reasonable accommodation during the application or interview process, please contact recruiting@livekit.io.", "summaryDescription" : "Staff Product Manager, Agent Observability at LiveKit. Define product strategy. Develop product roadmap", "createdAt" : "2026-06-14T18:40:31.088", "lastUpdated" : "2026-06-16T04:41:40.341", "ingestTimestamp" : "2026-06-14T18:40:31.088", "mongoId" : "6a2d351e74d8ee00a0b16891", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 225000, "salaryAnnualMax" : 265000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ "Roadmap planning" ], "skillCount" : 1, "jobCategory" : "product", "jobSubcategory" : "product_management", "seniorityLevel" : "Executive", "dataQualityScore" : 0.8888889, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2ab5d174d8ee00a06de5e1", "title" : "Senior Observability Architect", "company" : "Grafana Labs", "industry" : "Technology", "salary" : { "min" : 175000.0, "max" : 250000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Observability Architect in the US technology sector, adjusted for seniority and remote work." }, "location" : "USA (Remote)", "locations" : [ "USA (Remote)" ], "timestamp" : "2026-06-14T21:40:49.994", "fingerprint" : "a8fbda0fc2c1b694c629f652eddcae23668364b83a289bc4b5414bab6711b7d9", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.greenhouse.io/grafanalabs/jobs/6013689004", "externalId" : "6013689004", "industryFunction" : { }, "structuredLocations" : [ { "country" : "United States", "continent" : "na", "workMode" : "remote" } ], "locationText" : "United States", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Kubernetes, Observability", "professionalSkills" : [ "Systems thinking", "Architecture design", "Customer impact", "Technical ownership", "Strategic leadership", "Value realization", "Customer success", "Technical roadmaps", "Cost optimization", "Product adoption", "ROI assessment" ], "hardSkillsList" : [ "Troubleshooting", "Technical reviews", "Health checks", "Best practices", "Technical roadmaps", "Cost optimization", "Product adoption", "Customer lifecycle management", "Training sessions", "Workshops", "Technical documentation", "Client metrics", "Client achievements" ], "hardSkills" : [ { "name" : "Troubleshooting", "level" : "intermediate" }, { "name" : "Technical reviews", "level" : "intermediate" }, { "name" : "Health checks", "level" : "intermediate" }, { "name" : "Best practices", "level" : "intermediate" }, { "name" : "Technical roadmaps", "level" : "intermediate" }, { "name" : "Cost optimization", "level" : "intermediate" }, { "name" : "Product adoption", "level" : "intermediate" }, { "name" : "Customer lifecycle management", "level" : "intermediate" }, { "name" : "Training sessions", "level" : "intermediate" }, { "name" : "Workshops", "level" : "intermediate" }, { "name" : "Technical documentation", "level" : "intermediate" }, { "name" : "Client metrics", "level" : "intermediate" }, { "name" : "Client achievements", "level" : "intermediate" } ], "majorSkills" : "Observability architecture, Customer success, Technical partnership", "majorSkillsList" : [ "Observability architecture", "Customer success", "Technical partnership" ], "coreResponsibilities" : "Serve as primary technical point of contact, Design observability maturity journey, Provide expert-level troubleshooting, Conduct regular technical reviews, Conduct health checks, Assist in RCA, Advise clients on best practices, Advise clients on strategies, Collaborate to develop technical roadmaps, Collaborate to execute technical roadmaps, Identify opportunities for cost optimization, Identify opportunities to expand use, Identify opportunities for adoption, Develop strong relationships, Maintain long-term relationships, Own customer lifecycle, Drive adoption of product suite, Drive effective use of product suite, Maximize customer value, Ensure customer ROI, Act as voice of customer, Advocate for customer needs, Advocate for customer priorities, Advocate for customer feature requests, Conduct training sessions, Conduct workshops, Educate clients on technology, Work, account teams, Conduct regular reviews, Identify areas for improvement, Calculate ROI, Assess client satisfaction, Discuss upcoming needs, Discuss upcoming projects, Prepare reports on client metrics, Present reports on client metrics, Prepare reports on achievements, Present reports on achievements, Prepare reports on areas of focus, Present reports on areas of focus", "teamCollaboration" : "Remote-first internal teams; Worldwide customers; Account teams; Engagement Managers; Onboarding Solutions Architects; Engineering; Product Management", "projectManagementSkills" : [ "Technical roadmaps" ], "domainKnowledge" : "Observability solutions; Modern infrastructure; Application environments", "domainList" : [ "observability-solutions", "modern-infrastructure", "application-environments" ], "domainSpecificKnowledge" : [ "Observability solutions", "Modern infrastructure", "Application environments" ], "toolProficiency" : [ "CRM software", "Ticketing systems" ], "communicationSkills" : "Written communication; Oral communication; Technical documentation; Client presentations", "documentationSkills" : "Technical documentation; Guides; Tutorials", "problemSolvingSkills" : "Problem-solving; Analytical skills; Troubleshooting; Root cause analysis", "specialRequirements" : "25% travel", "outcomesObjectives" : "Ensure client success; Achieve business goals; Maximize value from platform; Ensure return on investment", "qualificationsBasic" : "Bachelor's degree in Computer Science, Information Technology, Math or a related field (or equivalent experience), 5+ years of experience in a technical support, technical account management, consulting, SE or Professional Services role within the technology industry, Experience deploying and operating Kubernetes, Understanding of observability solutions", "qualificationsPreferred" : "Grafana, Prometheus, and Loki a plus, Observability expertise, preferably architect level", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Grafana Labs, the company behind the open observability cloud, is founded on the principles of open source, open standards, open ecosystems, and open culture. Grafana Cloud, our fully managed observability platform, is flexible and built for scale. With Grafana Cloud's actually useful AI, organizations can see, understand, and act on all their disparate data to move at the speed of their ambitions. Today, more than 35 million users and 7,000+ customers – including Anthropic, Bloomberg, NVIDIA, Microsoft, and Salesforce – trust Grafana Labs to ensure reliability of their applications and systems, resolve incidents quickly, and optimize their telemetry to reduce noise and cost. We are a 100% remote company with 1,600+ team members across 40+ countries, and we’re backed by leading investors including Lightspeed Venture Partners, Sequoia Capital, GIC, Coatue, J. P. Morgan, CapitalG, and Lead Edge Capital. Learn more at grafana.com and follow us on LinkedIn and X. We’re scaling fast and staying true to what makes us different: an open-source legacy, a global collaborative culture, and a passion for meaningful work. Our team thrives in an innovation-driven environment where transparency, autonomy, and trust fuel everything we do. You may not meet every requirement, and that’s okay. If this role excites you, we’d love you to raise your hand for what could be a truly career-defining opportunity. The Opportunity: At Grafana Labs, we’re redefining what post-sales technical partnership looks like—and it starts with the Observability Architect. This is a role for deeply technical experts who are ready to step into strategic leadership with our most important customers. If you thrive at the intersection of systems thinking, architecture design, and customer impact—this is your stage. As an Observability Architect, you will be the technical owner of long-term customer success. You’ll architect and guide the implementation of complex observability solutions across a wide range of modern infrastructure and application environments. You’ll build strategic relationships with engineers, SREs, and architects—ensuring Grafana’s technology is not just deployed, but deeply embedded into mission-critical systems. Working hand-in-hand with our Engagement Managers, you’ll lead technical discovery, design, onboarding, and enablement—all with a focus on delivering tangible outcomes. You’ll spot patterns, solve hard problems, and guide customers through their observability maturity curve with authority and clarity. You’ll also represent the technical voice of our customers internally—shaping product feedback and roadmap priorities by working closely with Engineering and Product Management. This is a hands-on, high-impact role for those who want to go deep, stay technical, and directly influence customer success at scale. Join us and become part of the most respected observability team in the industry. What You'll Be Doing: Serve as the primary technical point of contact for a portfolio of Grafana customers. Design the observability maturity journey of customers and assist them on that path. Provide expert-level troubleshooting and guidance to drive adoption. Conduct regular technical reviews and health checks to ensure client success. Assist in RCA to understand issues that affect customer satisfaction, retention, and overall product experience. Advise clients on best practices and strategies for leveraging our technology to achieve their business goals Collaborate with clients to develop and execute technical roadmaps. Identify opportunities for clients to optimize their cost, expand their use of our solutions and drive adoption of new products and features. Develop and maintain strong, long-term relationships with key stakeholders. With the support of our Engagement Managers and Onboarding Solutions Architects, own customer lifecycle. Drive the adoption and effective use of our product suite within your customer portfolio to maximize their value from our platform and ensure a strong return on investment. Act as the voice of the customer within the company, advocating for their needs, priorities and feature requests. Conduct training sessions and workshops to educate clients on our technology. Develop and deliver technical documentation, guides, and tutorials. Work alongside account teams to participate in and/or conduct regular reviews with customers to identify areas for improvement, calculate ROI, assess their satisfaction, and discuss upcoming needs and projects. Prepare and present reports on client metrics, achievements, and areas of focus. What Makes You a Great Fit: Located on the West Coast Bachelor’s degree in Computer Science, Information Technology, Math or a related field (or equivalent experience). Experience deploying and operating Kubernetes. 5+ years of experience in a technical support, technical account management, consulting, SE or Professional Services role within the technology industry. Strong understanding of observability solutions. Grafana, Prometheus, and Loki a plus. Proven ability to manage multiple clients and projects simultaneously. Excellent problem-solving and analytical skills. Outstanding communication and interpersonal skills. Experience with relevant tools and technologies, e.g., CRM software, ticketing systems, specific programming languages. Ability to travel as needed to meet with clients (up to 25%). Identify and provide timely workarounds and solutions to meet a customer’s business needs. You have some observability expertise, preferably architect level First class written and oral communication skills to collaborate with our remote-first internal teams and with our worldwide customers. Ability to articulate our value proposition and the technical advantages of our products You will love solving technical challenges and thrive on bringing creative solutions to our customers Bonus Points For: 5+ years of technical sales, TAM or other post sales technical experience, ideally with open source technologies, or in the observability space. Great at connecting product usage to value (ROI). Great at managing customer lifecycle. You will be creative in solving customer adoption challenges. You can proactively assist customers with technical issues that may arise and assist in the troubleshooting and root cause analysis. You should have a technical mindset and a desire to grow technically. Great candidates may be a recent grad of a coding bootcamp or have previous post-sales or engineering experience–we are excited to see what unique experiences and skill sets you bring to the table! In the US, the OTE compensation range for this role is $204,000 - $260,000. Actual compensation may vary based on level, experience, and skillset as assessed throughout the interview process. All of our roles include Restricted Stock Units (RSUs), giving every team member ownership in Grafana Labs' success. We believe in shared outcomes—RSUs help us stay aligned and invested as we scale globally. *Compensation ranges are country specific. If you are applying for this role from a different location than listed above, your recruiter will discuss your specific market’s defined pay range & benefits at the beginning of the process. Why You’ll Thrive at Grafana Labs: 100% Remote, Global Culture - As a remote-only company, we bring together talent from around the world, united by a culture of collaboration and shared purpose. Scaling Organization – Tackle meaningful work in a high-growth, ever-evolving environment. Transparent Communication – Expect open decision-making and regular company-wide updates. Innovation-Driven – Autonomy and support to ship great work and try new things. Open Source Roots – Built on community-driven values that shape how we work. Empowered Teams – High trust, low ego culture that values outcomes over optics. Career Growth Pathways – Defined opportunities to grow and develop your career. Approachable Leadership – Transparent execs who are involved, visible, and human. Passionate People – Join a team of smart, supportive folks who care deeply about what they do. In-Person onboarding - We want you to thrive from day 1 with your fellow new ‘Grafanistas’ to learn all about what we do and how we do it. Balance is Key - We operate a global annual leave policy of 30 days per annum. 3 days of your annual leave entitlement are reserved for Grafana Shutdown Days to allow the team to really disconnect. *We will comply with local legislation where applicable. Equal Opportunity Employer: Grafana Labs is an equal opportunities employer. We welcome applications from everyone regardless of race, colour, nationality, origin, caste, sex, gender reassignment identity or expression, sexual orientation, age, religion or belief, disability, veteran status, genetic information, pregnancy, maternity, marital, family or carer status, or any other characteristic which is protected by local law. We believe that equality and diversity build a strong organisation, and we work hard to ensure that is the foundation of our organisation as we grow. Grafana Labs may utilize AI tools in its recruitment process to assist in matching information provided in CVs to job postings. The recruitment team will continue to review inbound CVs manually to identify alignment with current openings. #LI-Remote For information about how your personal data is used once you’ve applied to a job, check out our privacy policy.", "summaryDescription" : "Senior Observability Architect at Grafana Labs. Skills: Observability architecture, Customer success, Technical partnership. Serve as primary technical point of contact. Design observability maturity journey", "postedDate" : "2026-06-11T22:34:21.957", "createdAt" : "2026-06-11T22:34:21.957", "lastUpdated" : "2026-06-14T21:40:49.994", "ingestTimestamp" : "2026-06-11T22:34:21.957", "mongoId" : "6a2ab5d174d8ee00a06de5e1", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 175000, "salaryAnnualMax" : 250000, "salaryBand" : "150k-200k", "hasSalary" : true, "allSkills" : [ "Troubleshooting", "Technical reviews", "Health checks", "Best practices", "Technical roadmaps", "Cost optimization", "Product adoption", "Customer lifecycle management", "Training sessions", "Workshops", "Technical documentation", "Client metrics", "Client achievements", "Observability architecture", "Customer success", "Technical partnership", "Systems thinking", "Architecture design", "Customer impact", "Technical ownership", "Strategic leadership", "Value realization", "ROI assessment", "Observability solutions", "Modern infrastructure", "Application environments", "CRM software", "Ticketing systems" ], "skillCount" : 28, "jobCategory" : "customer-service", "jobSubcategory" : "customer-experience", "dataQualityScore" : 0.8888889, "daysOld" : 2, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology" }, { "id" : "6a2c799674d8ee00a0941f6f", "title" : "Senior Java Engineer - Distributed Systems - Elasticsearch", "company" : "Elastic", "industry" : "Technology", "salary" : { "min" : 4500000.0, "max" : 7500000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Java Engineer in the Technology industry, adjusted for seniority and global remote work." }, "location" : "Distributed, Global", "locations" : [ "Distributed", "Global" ], "timestamp" : "2026-06-16T02:53:59.438", "fingerprint" : "67bd789e6a973c7374624f7674d06be44201493f73812d0cb2b8ac0a4d720c02", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://jobs.elastic.co/jobs?gh_jid=8001191&gh_jid=8001191", "externalId" : "8001191", "industryFunction" : { }, "structuredLocations" : [ { "workMode" : "remote" } ], "locationText" : "", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Java, Spring Boot, Kafka, Redis, Elasticsearch, Microservices, AWS, GCP, Azure, Docker, Kubernetes, SQL, NoSQL, Linux, Unix, Git, CI/CD, Terraform, Ansible", "professionalSkills" : [ "System design", "Problem solving", "Troubleshooting" ], "hardSkillsList" : [ "Distributed systems", "Performance tuning", "Data streaming", "Large-scale data processing" ], "hardSkills" : [ { "name" : "Distributed systems", "level" : "intermediate" }, { "name" : "Performance tuning", "level" : "intermediate" }, { "name" : "Data streaming", "level" : "intermediate" }, { "name" : "Large-scale data processing", "level" : "intermediate" } ], "majorSkills" : "Distributed systems, Elasticsearch, Java, Microservices", "majorSkillsList" : [ "Distributed systems", "Elasticsearch", "Java", "Microservices" ], "coreResponsibilities" : "Design and implement distributed systems, Develop and maintain microservices, Optimize Elasticsearch performance, Build and manage CI/CD pipelines, Ensure system reliability and scalability, Troubleshoot and resolve production issues, Collaborate with cross-functional teams, Write clean, maintainable code, Participate in code reviews, Contribute to system architecture discussions, Develop and maintain monitoring and alerting systems, Manage cloud infrastructure, Implement infrastructure as code", "teamCollaboration" : "Cross-functional teams; Code reviews", "projectManagementSkills" : [ "Agile", "Scrum", "CI/CD" ], "domainKnowledge" : "Distributed systems; Microservices architecture; Cloud platforms; Containerization; Data streaming; Observability", "domainList" : [ "distributed-systems", "microservices-architecture", "cloud-platforms", "containerization", "data-streaming", "observability" ], "domainSpecificKnowledge" : [ "Distributed systems", "Microservices architecture", "Cloud platforms", "Containerization", "Data streaming", "Observability" ], "toolProficiency" : [ "Docker", "Kubernetes", "Git", "Terraform", "Ansible", "JIRA" ], "problemSolvingSkills" : "Root cause analysis; Troubleshooting; Performance tuning", "qualificationsBasic" : "5+ years of experience in software development, Experience with distributed systems, Experience with Elasticsearch, Experience with Java, Experience with Spring Boot, Experience with Kafka, Experience with Redis, Experience with microservices architecture, Experience with cloud platforms (AWS, GCP, Azure), Experience with CI/CD pipelines, Experience with containerization (Docker, Kubernetes), Experience with SQL and NoSQL databases, Experience with monitoring and alerting tools, Experience with Linux/Unix environments, Experience with Git", "qualificationsPreferred" : "Experience with performance tuning, Experience with distributed tracing, Experience with observability tools, Experience with data streaming technologies, Experience with machine learning, Experience with AI, Experience with large-scale data processing, Experience with security best practices, Experience with infrastructure as code (Terraform, Ansible), Experience with Kubernetes", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI. What Is The Role: We are on the lookout for a Senior Software Engineer to join our Elasticsearch - Distributed Systems team and focus on how Elasticsearch provides scale, performance, and resilience. This team owns how nodes in an Elasticsearch cluster communicate, and how data are indexed, allocated, and replicated across nodes. What You Will Be Doing: Improving Elasticsearch’s components that support concurrent and consistent indexing across multiple machines. Maintaining our cluster coordination system to keep performance high even though nodes come and go from the cluster and data moves around, while maintaining the safety and liveness properties of the system as a whole. Pushing the limits on the number of shards, nodes, and petabytes that Elasticsearch can handle today Looking into all kinds of issues, including performance or concurrency issues, and proposing solutions. Supporting our support engineers with the harder problems. What You Bring: A strong background in distributed systems and consensus algorithms. You have strong skills in core Java and are conversant in the standard library of data structures and concurrency constructs, as well as newer language features. You have a deep technical proficiency in algorithms. You have shown your ability to understand and work on complex, highly distributed systems. You demonstrate the ability to build and debug features with a broad impact, running on multiple machines. You are able to own projects from beginning to end. This covers both technical design and working with others to develop needed components. Bonus Points: Data stores Search, analytics, Lucene Strong knowledge of the JDK Asynchronous event-driven network frameworks such as Netty Compensation for this role is in the form of base salary. This role does not have a variable compensation component. At Elastic, our compensation philosophy aims to provide fair, competitive and transparent remuneration. Salary ranges are established based on a combination of external market benchmarks, internal pay equity considerations, and the responsibilities and complexity associated with each role. This approach helps ensure consistency across comparable roles while remaining competitive within the relevant labour markets. The final compensation offered within the applicable range will be determined based on several objective factors, including relevant professional experience, level of skills and expertise, alignment with the role requirements, and the overall scope and complexity of the position. The typical starting salary range for this role is: 272.000 Lei—430.200 Lei RON Additional Information - We Take Care of Our People As a distributed company, diversity drives our identity. Whether you’re looking to launch a new career or grow an existing one, Elastic is the type of company where you can balance great work with great life. Your age is only a number. It doesn’t matter if you’re just out of college or your children are; we need you for what you can do. We strive to have parity of benefits across regions and while regulations differ from place to place, we believe taking care of our people is the right thing to do. Competitive pay based on the work you do here and not your previous salary Health coverage for you and your family in many locations Ability to craft your calendar with flexible locations and schedules for many roles Generous number of vacation days each year Increase your impact - We match up to $2000 (or local currency equivalent) for financial donations and service Up to 40 hours each year to use toward volunteer projects you love Embracing parenthood with minimum of 16 weeks of parental leave Different people approach problems differently. We need that. Elastic is an equal opportunity employer and is committed to creating an inclusive culture that celebrates different perspectives, experiences, and backgrounds. Qualified applicants will receive consideration for employment without regard to race, ethnicity, color, religion, sex, pregnancy, sexual orientation, gender perception or identity, national origin, age, marital status, protected veteran status, disability status, or any other basis protected by federal, state or local law, ordinance or regulation. We welcome individuals with disabilities and strive to create an accessible and inclusive experience for all individuals. To request an accommodation during the application or the recruiting process, please email candidate_accessibility@elastic.co. We will reply to your request within 24 business hours of submission. Applicants have rights under Federal Employment Laws, view posters linked below: Family and Medical Leave Act (FMLA) Poster; Pay Transparency Nondiscrimination Provision Poster; Employee Polygraph Protection Act (EPPA) Poster and Know Your Rights (Poster) Elasticsearch develops and distributes technology and information that is subject to U. S. and other countries’ export controls and licensing requirements for individuals who are located in or are nationals of the following sanctioned countries and regions: Belarus, Cuba, Iran, North Korea, Syria, or Russia, including the Ukrainian territories annexed by Russia (The Crimea region of Ukraine, The Donetsk People's Republic (DNR), The Luhansk People's Republic (LNR), Kherson or Zaporizhzhia). If you are located in or are a national of one of the listed countries or regions, an export license may be required as a condition of your employment in this role. Please note that national origin and/or nationality do not affect eligibility for employment with Elastic. Please see here for our Privacy Statement.", "summaryDescription" : "Senior Java Engineer - Distributed Systems - Elasticsearch at Elastic. Skills: Distributed systems, Elasticsearch, Java, Microservices. Design and implement distributed systems. Develop and maintain microservices", "postedDate" : "2026-06-14T20:08:34.290", "createdAt" : "2026-06-14T20:08:34.290", "lastUpdated" : "2026-06-16T02:53:59.438", "ingestTimestamp" : "2026-06-14T20:08:34.290", "mongoId" : "6a2c799674d8ee00a0941f6f", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ "Distributed systems", "Performance tuning", "Data streaming", "Large-scale data processing", "Elasticsearch", "Java", "Microservices", "System design", "Problem solving", "Troubleshooting", "Agile", "Scrum", "CI/CD", "Microservices architecture", "Cloud platforms", "Containerization", "Observability", "Docker", "Kubernetes", "Git", "Terraform", "Ansible", "JIRA" ], "skillCount" : 23, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a305d29f292fd229cf64dd0", "title" : "Director, Data Governance & Observability", "company" : "Versant", "industry" : "Entertainment", "salary" : { "min" : 225000.0, "max" : 325000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for Director, Data Governance & Observability in New York, USA, with adjustments for seniority, industry, and company size." }, "location" : "New York, NEW YORK, United States", "locations" : [ "New York", "NEW YORK", "United States" ], "timestamp" : "2026-06-16T10:08:08.610", "fingerprint" : "70adab77f9e1e5e91c7af9175e26a319e95d1023ac27b0564509a669bc8ee9aa", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Versant3/744000131962953-director-data-governance-observability", "externalId" : "744000131962953", "industryFunction" : { }, "structuredLocations" : [ { "city" : "New York", "state" : "New York", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "40.7127281,-74.0060152" } ], "locationText" : "New York, New York, United States", "employmentType" : "FULL_TIME", "experienceMinYears" : 10, "experienceMaxYears" : 15, "experienceLevel" : "director", "technicalSkills" : "SQL, Python", "professionalSkills" : [ "Data governance", "Data observability", "Data quality", "Data cataloging", "Data lineage", "Data security", "Data privacy", "Data modeling", "Data warehousing", "ETL", "ELT", "BI" ], "hardSkillsList" : [ "Data governance", "Data observability", "Data quality", "Data cataloging", "Data lineage", "Data security", "Data privacy", "Data modeling", "Data warehousing", "ETL", "ELT", "BI" ], "hardSkills" : [ { "name" : "Data governance", "level" : "intermediate" }, { "name" : "Data observability", "level" : "intermediate" }, { "name" : "Data quality", "level" : "intermediate" }, { "name" : "Data cataloging", "level" : "intermediate" }, { "name" : "Data lineage", "level" : "intermediate" }, { "name" : "Data security", "level" : "intermediate" }, { "name" : "Data privacy", "level" : "intermediate" }, { "name" : "Data modeling", "level" : "intermediate" }, { "name" : "Data warehousing", "level" : "intermediate" }, { "name" : "ETL", "level" : "intermediate" }, { "name" : "ELT", "level" : "intermediate" }, { "name" : "BI", "level" : "intermediate" } ], "majorSkills" : "Data governance, Data observability", "majorSkillsList" : [ "Data governance", "Data observability" ], "coreResponsibilities" : "Develop and implement data governance policies, Develop and implement data observability strategies, Establish and maintain data quality standards, Implement and manage data cataloging solutions, Implement and manage data lineage tracking, Ensure data security and privacy compliance, Oversee data modeling and data warehousing initiatives, Manage ETL/ELT processes, Collaborate with stakeholders to understand data needs, Provide guidance on data best practices, Monitor data systems for performance and issues, Identify and resolve data-related problems, Develop and deliver data governance training, Stay updated on industry trends and technologies", "teamCollaboration" : "Cross-functional teams; Data engineering teams; Data science teams; Business stakeholders", "domainKnowledge" : "Data governance frameworks; Data observability frameworks; Data quality frameworks; Data cataloging frameworks; Data lineage frameworks; Data security frameworks; Data privacy regulations", "domainList" : [ "data-governance-frameworks", "data-observability-frameworks", "data-quality-frameworks", "data-cataloging-frameworks", "data-lineage-frameworks", "data-security-frameworks", "data-privacy-regulations" ], "domainSpecificKnowledge" : [ "Data governance frameworks", "Data observability frameworks", "Data quality frameworks", "Data cataloging frameworks", "Data lineage frameworks", "Data security frameworks", "Data privacy regulations" ], "problemSolvingSkills" : "Data quality issues; Data security issues; Data privacy issues; Data system performance", "qualificationsBasic" : "5+ years experience in data governance, 5+ years experience in data observability, Experience with data quality frameworks, Experience with data cataloging tools, Experience with data lineage tools, Experience with data security best practices, Experience with data privacy regulations, Experience with data modeling, Experience with data warehousing concepts, Experience with ETL/ELT processes, Experience with SQL, Experience with Python", "qualificationsPreferred" : "Master's degree preferred, Experience with cloud data platforms, Experience with data governance tools, Experience with data observability tools, Experience with data cataloging solutions, Experience with data lineage solutions, Experience with data quality solutions, Experience with data security solutions, Experience with data privacy solutions, Experience with data modeling tools, Experience with data warehousing tools, Experience with ETL/ELT tools, Experience with BI tools, Experience with data governance frameworks, Experience with data observability frameworks, Experience with data quality frameworks, Experience with data cataloging frameworks, Experience with data lineage frameworks, Experience with data security frameworks, Experience with data privacy frameworks, Experience with data modeling frameworks, Experience with data warehousing frameworks, Experience with ETL/ELT frameworks, Experience with BI frameworks, Experience with data governance best practices, Experience with data observability best practices, Experience with data quality best practices, Experience with data cataloging best practices, Experience with data lineage best practices, Experience with data security best practices, Experience with data privacy best practices, Experience with data modeling best practices, Experience with data warehousing best practices, Experience with ETL/ELT best practices, Experience with BI best practices, Experience with data governance regulations, Experience with data observability regulations, Experience with data quality regulations, Experience with data cataloging regulations, Experience with data lineage regulations, Experience with data security regulations, Experience with data privacy regulations, Experience with data modeling regulations, Experience with data warehousing regulations, Experience with ETL/ELT regulations, Experience with BI regulations", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "VERSANT (Nasdaq: VSNT) is an industry-changing media and entertainment business and home to trusted brands that shape culture, inform audiences, and build lasting connections. It operates across four core markets: political news and opinion, business news and personal finance, golf, and sports and genre entertainment. These markets are served through a powerful portfolio of iconic and innovative brands, including CNBC, MS NOW, USA Network, Golf Channel, Oxygen, E!, SYFY, and Versant’s sports division USA Sports, along with complementary digital assets including Fandango, Rotten Tomatoes, GolfNow and GolfPass. Versant Media’s Data Platforms team is the central data store across the enterprise. We unify disparate systems into a secure, well-governed, real-time data environment that powers downstream products, analytics, and content delivery experiences. We are seeking a Director, Data Governance & Observability to establish and operationalize data governance as a first-class platform capability. This is a hands-on leadership role for someone who can both design and implement governance mechanisms in code, while also setting standards, prioritizing work, and partnering across the organization. This role will start as an individual contributor with leadership accountability , responsible for building the initial governance and observability foundations. Over time, the role is expected to grow into a people management position as scale and needs increase. The Director, Data Governance & Observability reports to the VP of Data Platforms and works in close partnership with Platform Development, Data Products & Solutions, and SRE. Responsibilities Data Governance & Contracts * Define and enforce data contracts across platform services and data products, including schemas, expectations, ownership, and change management * Establish standards for data lineage, metadata, and semantic consistency across the platform * Own definitions for data quality(freshness, completeness, correctness) and how those standards are validated * Partner with Platform Development to ensure governance requirements are embedded directly into pipelines, services, and APIs Observability & Reliability (Data-Level) * Define data-level SLIs and SLOs in partnership with the SRE organization * Ensure contract violations, quality failures, and freshness issues are observable and actionable * Build and maintain platform-facing health and operational dashboards related to data services * Contribute to light executive-level reporting on platform health and data reliability (not business analytics) Hands-On Platform Development * Write production code to implement governance and observability mechanisms (e.g., schema validation, contract enforcement, lineage capture) * Contribute to shared platform libraries, services, and tooling that make compliant behavior the default * Review designs and code to ensure governance considerations are addressed early Cross-Functional Leadership * Partner closely with: * Director, Platform Development on schemas, contracts, and platform enforcement patterns * Director, Data Products & Solutions on base dashboards, self-service enablement, and consumer-facing trust signals * SRE on alerting strategy, incident classification, and reliability standards * Help triage and prioritize governance-related intake and tradeoffs * Clearly communicate standards and expectations to engineering and non-engineering stakeholders Team Growth (Future) * Hire and mentor data platform engineers focused on governance and quality as needs scale * Gradually transition toward more people leadership and strategic ownership over time ## Qualifications * 10+ years Strong hands-on experience building production data or platform systems * Deep understanding of data governance concepts, including contracts, lineage, metadata, and quality * Experience defining and enforcing standards through code and automation, not just documentation * Solid software engineering foundation, including: * API and schema design * Modular or service-oriented architectures * Automated testing and CI/CD practices * Familiarity with observability concepts and working with SRE teams * Comfortable operating with high ownership in a lean, fast-moving environment * Strong collaborator who can work across platform, product, analytics, and operations teams Nice to Have * Experience working in large-scale enterprise or media environments * Familiarity with lakehouse architectures and ELT pipelines * Exposure to analytics or BI tooling (e.g., Tableau, Power BI) from a platform or enablement perspective * Experience modernizing or governing legacy data systems in cloud-native environments ## Additional Information As part of our selection process, external candidates may be required to attend an in-person interview with a VERSANT Media employee at one of our locations prior to a hiring decision. VERSANT Media's policy is to provide equal employment opportunities to all applicants and employees without regard to race, color, religion, creed, gender, gender identity or expression, age, national origin or ancestry, citizenship, disability, sexual orientation, marital status, pregnancy, veteran status, membership in the uniformed services, genetic information, or any other basis protected by applicable law. If you are a qualified individual with a disability or a disabled veteran and require support throughout the application and/or recruitment process as a result of your disability, you have the right to request a reasonable accommodation. You can submit your request to [candidateaccessibility@versantmedia.com](mailto:candidateaccessibility@versantmedia.com). VERSANT Media is committed to fair and equitable compensation practices. We include a good faith pay range for each position to comply with applicable state and local pay transparency laws and to promote equity across our organization. Actual compensation will be based on factors such as the candidate's skills, qualifications, experience, and location and may include additional forms of compensation and benefits such as health insurance, retirement plans, paid time off, etc. VERSANT Media is not accepting unsolicited assistance from search firms for this employment opportunity. All resumes submitted by search firms to any employee at VERSANT via-email, the Internet, or in any form and/or method without a valid written Statement of Work in place for this position from VERSANT's Talent Acquisition team will be deemed the sole property of VERSANT. No fee will be paid in the event the candidate is hired by VERSANT as a result of the referral or through other means.", "summaryDescription" : "Director, Data Governance & Observability at Versant. Skills: Data governance, Data observability. Develop and implement data governance policies. Develop and implement data observability strategies", "postedDate" : "2026-06-12T18:37:58.000", "createdAt" : "2026-06-16T00:14:31.454", "lastUpdated" : "2026-06-16T10:08:08.610", "ingestTimestamp" : "2026-06-16T00:14:31.454", "mongoId" : "6a305d29f292fd229cf64dd0", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 225000, "salaryAnnualMax" : 325000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ "Data governance", "Data observability", "Data quality", "Data cataloging", "Data lineage", "Data security", "Data privacy", "Data modeling", "Data warehousing", "ETL", "ELT", "BI", "Data governance frameworks", "Data observability frameworks", "Data quality frameworks", "Data cataloging frameworks", "Data lineage frameworks", "Data security frameworks", "Data privacy regulations" ], "skillCount" : 19, "jobCategory" : "engineering", "jobSubcategory" : "data", "seniorityLevel" : "Director", "dataQualityScore" : 1.0, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Media", "llmIndustryConfidence" : 0.97 }, { "id" : "6a2c5f4074d8ee00a08ea5b9", "title" : "Staff Observability Platform Engineer", "company" : "Nscale", "industry" : "Technology", "salary" : { "min" : 215000.0, "max" : 305000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for Staff Observability Platform Engineer in the US, adjusted for lead seniority and technology industry." }, "location" : "US", "locations" : [ "US" ], "timestamp" : "2026-06-15T00:39:12.906", "fingerprint" : "de0efd1f7f2f88e1ad0529f523002881f6766b25af655c86722b26c9c49b206c", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.eu.greenhouse.io/nscaleoperationsukltd/jobs/4890586101", "externalId" : "4890586101", "industryFunction" : { }, "structuredLocations" : [ { "country" : "United States", "continent" : "na", "workMode" : "onsite" } ], "locationText" : "United States", "experienceMinYears" : 8, "experienceMaxYears" : 15, "experienceLevel" : "Staff", "technicalSkills" : "Prometheus, Thanos, VictoriaMetrics, Grafana, Loki, Tempo, OpenTelemetry, ClickHouse, Elastic, Go, Python, Kubernetes, Terraform, Ansible, Kafka, Vector, Fluent Bit", "professionalSkills" : [ "Platform engineering", "Infrastructure engineering", "Observability engineering", "System design", "Architectural decisions", "Engineering best practices", "Operational efficiency", "Developer experience" ], "hardSkillsList" : [ "Telemetry pipelines", "Cardinality management", "Performance optimization", "Incident response" ], "softSkillsList" : [ "Leadership", "Mentoring" ], "hardSkills" : [ { "name" : "Telemetry pipelines", "level" : "intermediate" }, { "name" : "Cardinality management", "level" : "intermediate" }, { "name" : "Performance optimization", "level" : "intermediate" }, { "name" : "Incident response", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Leadership" }, { "name" : "Mentoring" } ], "majorSkills" : "Observability platforms, GPU infrastructure, AI infrastructure", "majorSkillsList" : [ "Observability platforms", "GPU infrastructure", "AI infrastructure" ], "coreResponsibilities" : "Design observability platforms, Build observability platforms, Evolve observability platforms, Lead implementation of scalable observability solutions, Partner with SRE, infrastructure, platform, and AI/ML teams, Embed observability throughout lifecycle, Drive improvements in monitoring coverage, Drive improvements in alert quality, Drive improvements in service health visibility, Drive improvements in incident response effectiveness, Develop standards for observability adoption, Develop frameworks for observability adoption, Develop reusable patterns for observability adoption, Identify reliability risks, Identify operational blind spots, Address risks proactively, Contribute to architectural decisions, Lead technical initiatives, Lead projects to improve platform scalability, Lead projects to improve platform reliability, Lead projects to improve platform operational efficiency, Mentor engineers, Provide technical guidance, Participate in incident investigations, Participate in postmortems, Translate operational learnings into platform improvements, Evaluate new observability technologies, Evaluate new observability practices", "teamCollaboration" : "Partnering across teams; Cross-functional teams; Engineering teams", "projectManagementSkills" : [ "Technical initiatives" ], "domainKnowledge" : "Cloud-native environments; Distributed systems; GPU clusters; AI workloads; AI/ML; HPC; Large-scale compute; Model training; Inference workloads; GPU utilization; Distributed AI systems", "domainList" : [ "cloud-native-environments", "distributed-systems", "gpu-clusters", "ai-workloads", "ai-ml", "hpc", "large-scale-compute", "model-training", "inference-workloads", "gpu-utilization", "distributed-ai-systems" ], "domainSpecificKnowledge" : [ "Cloud-native environments", "Distributed systems", "GPU clusters", "AI workloads", "AI/ML", "HPC", "Large-scale compute", "Model training", "Inference workloads", "GPU utilization", "Distributed AI systems" ], "toolProficiency" : [ "Prometheus", "Thanos", "VictoriaMetrics", "Grafana", "Loki", "Tempo", "OpenTelemetry", "ClickHouse", "Elastic", "Terraform", "Ansible", "Kafka", "Vector", "Fluent Bit" ], "communicationSkills" : "Explain technical tradeoffs; Align stakeholders", "innovationCreativity" : "Relentless innovation", "problemSolvingSkills" : "Solving difficult infrastructure problems", "qualificationsBasic" : "6+ years experience in SRE, platform engineering, infrastructure engineering, observability engineering, or related disciplines, Experience building and operating observability platforms in cloud-native, distributed environments, Deep hands-on experience with Prometheus, Thanos, VictoriaMetrics, Grafana, Loki, Tempo, OpenTelemetry, ClickHouse, Elastic, or similar platforms, Software engineering skills with proficiency in Go, Python, or equivalent languages, Experience operating and troubleshooting Kubernetes-based platforms at scale, Understanding of monitoring, logging, tracing, telemetry pipelines, and modern observability practices, Experience designing systems with scalability, reliability, performance, and operational simplicity in mind, Proficiency with Infrastructure-as-Code tools such as Terraform, Ansible, or equivalent, Ability to lead technical initiatives and influence engineering decisions across multiple teams, Excellent communication skills with the ability to explain technical tradeoffs and align stakeholders around pragmatic solutions", "qualificationsPreferred" : "Operating observability systems in GPU, AI/ML, HPC, or large-scale compute environments, Familiarity with Slurm, Kubernetes GPU scheduling, or AI infrastructure platforms, Experience with high-volume telemetry pipelines and streaming technologies such as Kafka, Vector, or Fluent Bit, Knowledge of observability challenges related to model training, inference workloads, GPU utilization, and distributed AI systems, Experience mentoring engineers and helping grow technical capability across teams", "remoteFriendly" : false, "rawDescription" : "About Nscale Nscale is the GPU cloud engineered for AI. We provide cost-effective, high-performance infrastructure for AI start-ups and large enterprise customers. Nscale simplifies AI development while enabling superior results, supporting strategic business outcomes such as cost management, rapid innovation, and environmental responsibility. We thrive on a culture of relentless innovation, ownership, and accountability, where every team member takes pride in their work and drives it with excellence and urgency. As an Nscaler, you'll build trust through openness and transparency while contributing to the technology that powers the future. About the Role As a Staff Observability Platform Engineer, you'll play a critical role in building and evolving Nscale's observability platform, enabling deep visibility into GPU clusters, AI workloads, and the infrastructure that powers them. You view observability as a product, not simply a collection of tools. You'll help define and implement scalable, reliable observability solutions that empower engineering teams to understand system behavior, diagnose issues quickly, and operate complex distributed systems with confidence. You'll combine technical leadership with hands-on engineering, partnering across SRE, infrastructure, platform, and AI/ML teams to improve reliability, operational efficiency, and developer experience. You'll influence architectural decisions, establish engineering best practices, and help drive the evolution of observability capabilities across the organization. This is a role for someone who enjoys solving difficult infrastructure problems, building platforms that scale, and helping engineering teams succeed through better visibility and operational insight. What You'll Do Design, build, and evolve observability platforms across metrics, logs, traces, alerting, and telemetry pipelines. Lead the implementation of scalable observability solutions that support Nscale's growing GPU and AI infrastructure. Partner with SRE, infrastructure, platform, and AI/ML teams to ensure observability is embedded throughout the software and infrastructure lifecycle. Drive improvements in monitoring coverage, alert quality, service health visibility, and incident response effectiveness. Develop standards, frameworks, and reusable patterns that simplify observability adoption across engineering teams. Identify reliability risks and operational blind spots, helping teams proactively address them before they impact customers. Contribute to architectural decisions around telemetry collection, storage, retention, cardinality management, and performance optimization. Lead technical initiatives and projects that improve platform scalability, reliability, and operational efficiency. Mentor engineers and provide technical guidance through design reviews, code reviews, and knowledge sharing. Participate in incident investigations and postmortems, translating operational learnings into durable platform improvements. Evaluate new observability technologies and practices, balancing innovation with operational simplicity and long-term maintainability. About You 6+ years of experience in SRE, platform engineering, infrastructure engineering, observability engineering, or related disciplines. Strong experience building and operating observability platforms in cloud-native, distributed environments. Deep hands-on experience with several of the following technologies: Prometheus, Thanos, VictoriaMetrics, Grafana, Loki, Tempo, OpenTelemetry, ClickHouse, Elastic, or similar platforms. Strong software engineering skills with proficiency in Go, Python, or equivalent languages. Experience operating and troubleshooting Kubernetes-based platforms at scale. Strong understanding of monitoring, logging, tracing, telemetry pipelines, and modern observability practices. Experience designing systems with scalability, reliability, performance, and operational simplicity in mind. Proficiency with Infrastructure-as-Code tools such as Terraform, Ansible, or equivalent. Ability to lead technical initiatives and influence engineering decisions across multiple teams. Excellent communication skills with the ability to explain technical tradeoffs and align stakeholders around pragmatic solutions. Preferred Experience operating observability systems in GPU, AI/ML, HPC, or large-scale compute environments. Familiarity with Slurm, Kubernetes GPU scheduling, or AI infrastructure platforms. Experience with high-volume telemetry pipelines and streaming technologies such as Kafka, Vector, or Fluent Bit. Knowledge of observability challenges related to model training, inference workloads, GPU utilization, and distributed AI systems. Experience mentoring engineers and helping grow technical capability across teams. Equal Opportunities Statement We strongly encourage applications from people of color, the LGBTQ+ community, people with disabilities, neurodivergent individuals, parents, carers, and people from lower socio-economic backgrounds. If there's anything we can do to accommodate your specific situation, please let us know. Note: Responsibilities outlined are not exhaustive and may evolve as business needs change. For information on how Nscale handles candidate personal data, please see our Employee & Candidate Privacy Notice: Here.", "summaryDescription" : "Staff Observability Platform Engineer at Nscale. Skills: Observability platforms, GPU infrastructure, AI infrastructure. Design observability platforms. Build observability platforms", "postedDate" : "2026-06-12T22:30:55.256", "createdAt" : "2026-06-12T22:30:55.256", "lastUpdated" : "2026-06-15T00:39:12.906", "ingestTimestamp" : "2026-06-12T22:30:55.256", "mongoId" : "6a2c5f4074d8ee00a08ea5b9", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 215000, "salaryAnnualMax" : 305000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ "Telemetry pipelines", "Cardinality management", "Performance optimization", "Incident response", "Leadership", "Mentoring", "Observability platforms", "GPU infrastructure", "AI infrastructure", "Platform engineering", "Infrastructure engineering", "Observability engineering", "System design", "Architectural decisions", "Engineering best practices", "Operational efficiency", "Developer experience", "Technical initiatives", "Cloud-native environments", "Distributed systems", "GPU clusters", "AI workloads", "AI/ML", "HPC", "Large-scale compute", "Model training", "Inference workloads", "GPU utilization", "Distributed AI systems", "Prometheus", "Thanos", "VictoriaMetrics", "Grafana", "Loki", "Tempo", "OpenTelemetry", "ClickHouse", "Elastic", "Terraform", "Ansible", "Kafka", "Vector", "Fluent Bit" ], "skillCount" : 43, "jobCategory" : "operations", "jobSubcategory" : "ai-infrastructure-operations", "dataQualityScore" : 0.8888889, "daysOld" : 2, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology" }, { "id" : "6a2c799674d8ee00a0941f6e", "title" : "Senior Java Engineer - Distributed Systems - Elasticsearch", "company" : "Elastic", "industry" : "Technology", "salary" : { "min" : 4500000.0, "max" : 7000000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Java Engineer in the Technology industry, adjusted for seniority and global remote work, with a focus on the Indian market due to the currency requested." }, "location" : "Distributed, Global", "locations" : [ "Distributed", "Global" ], "timestamp" : "2026-06-16T06:54:33.374", "fingerprint" : "cf5c1d3db0898d183b5d99675796d50c40e66bd3023945ab1d543120b474142d", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://jobs.elastic.co/jobs?gh_jid=8001192&gh_jid=8001192", "externalId" : "8001192", "industryFunction" : { }, "structuredLocations" : [ { "workMode" : "remote" } ], "locationText" : "", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Java, Spring Boot, Kafka, Redis, Elasticsearch, Microservices, AWS, GCP, Azure, Docker, Kubernetes, SQL, NoSQL, CI/CD, Go, GRPC", "professionalSkills" : [ "System design", "Performance tuning", "Security best practices", "Agile methodologies" ], "hardSkillsList" : [ "Distributed systems", "Microservices architecture", "Cloud platforms", "Containerization", "Monitoring and alerting", "Performance optimization", "Security best practices" ], "hardSkills" : [ { "name" : "Distributed systems", "level" : "intermediate" }, { "name" : "Microservices architecture", "level" : "intermediate" }, { "name" : "Cloud platforms", "level" : "intermediate" }, { "name" : "Containerization", "level" : "intermediate" }, { "name" : "Monitoring and alerting", "level" : "intermediate" }, { "name" : "Performance optimization", "level" : "intermediate" }, { "name" : "Security best practices", "level" : "intermediate" } ], "majorSkills" : "Distributed systems, Elasticsearch, Java, Microservices", "majorSkillsList" : [ "Distributed systems", "Elasticsearch", "Java", "Microservices" ], "coreResponsibilities" : "Design, build, and maintain scalable microservices, Develop and optimize Elasticsearch solutions, Implement and manage CI/CD pipelines, Ensure system reliability and performance, Troubleshoot and resolve production issues, Collaborate with cross-functional teams, Write clean, maintainable, and testable code, Participate in code reviews, Stay up-to-date with new technologies", "teamCollaboration" : "Cross-functional teams; Code reviews", "projectManagementSkills" : [ "Agile methodologies" ], "domainKnowledge" : "Distributed systems; Microservices architecture; Elasticsearch; Cloud platforms", "domainList" : [ "distributed-systems", "microservices-architecture", "elasticsearch", "cloud-platforms" ], "domainSpecificKnowledge" : [ "Distributed systems", "Microservices architecture", "Elasticsearch", "Cloud platforms" ], "toolProficiency" : [ "Docker", "Kubernetes", "AWS", "GCP", "Azure", "CI/CD tools" ], "continuousLearning" : "Stay up-to-date with new technologies", "problemSolvingSkills" : "Troubleshoot and resolve production issues; Performance tuning; Optimization", "qualificationsBasic" : "5+ years of experience in software development, Experience with distributed systems, Experience with Elasticsearch, Experience with Java, Experience with Spring Boot, Experience with Kafka, Experience with Redis, Experience with microservices architecture, Experience with cloud platforms (AWS, GCP, Azure), Experience with CI/CD pipelines, Experience with containerization (Docker, Kubernetes), Experience with SQL and NoSQL databases, Experience with monitoring and alerting tools, Experience with performance tuning and optimization, Experience with security best practices, Experience with Agile methodologies", "qualificationsPreferred" : "Experience with Go, Experience with gRPC, Experience with distributed tracing, Experience with observability tools, Experience with data streaming platforms, Experience with machine learning, Master's degree in Computer Science or related field, Contributions to open-source projects", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI. What Is The Role: We are on the lookout for a Senior Software Engineer to join our Elasticsearch - Distributed Systems team and focus on how Elasticsearch provides scale, performance, and resilience. This team owns how nodes in an Elasticsearch cluster communicate, and how data are indexed, allocated, and replicated across nodes. What You Will Be Doing: Improving Elasticsearch’s components that support concurrent and consistent indexing across multiple machines. Maintaining our cluster coordination system to keep performance high even though nodes come and go from the cluster and data moves around, while maintaining the safety and liveness properties of the system as a whole. Pushing the limits on the number of shards, nodes, and petabytes that Elasticsearch can handle today Looking into all kinds of issues, including performance or concurrency issues, and proposing solutions. Supporting our support engineers with the harder problems. What You Bring: A strong background in distributed systems and consensus algorithms. You have strong skills in core Java and are conversant in the standard library of data structures and concurrency constructs, as well as newer language features. You have a deep technical proficiency in algorithms. You have shown your ability to understand and work on complex, highly distributed systems. You demonstrate the ability to build and debug features with a broad impact, running on multiple machines. You are able to own projects from beginning to end. This covers both technical design and working with others to develop needed components. Bonus Points: Data stores Search, analytics, Lucene Strong knowledge of the JDK Asynchronous event-driven network frameworks such as Netty Compensation for this role is in the form of base salary. This role does not have a variable compensation component. At Elastic, our compensation philosophy aims to provide fair, competitive and transparent remuneration. Salary ranges are established based on a combination of external market benchmarks, internal pay equity considerations, and the responsibilities and complexity associated with each role. This approach helps ensure consistency across comparable roles while remaining competitive within the relevant labour markets. The final compensation offered within the applicable range will be determined based on several objective factors, including relevant professional experience, level of skills and expertise, alignment with the role requirements, and the overall scope and complexity of the position. The typical starting salary range for this role is: €67.000—€106.000 EUR Additional Information - We Take Care of Our People As a distributed company, diversity drives our identity. Whether you’re looking to launch a new career or grow an existing one, Elastic is the type of company where you can balance great work with great life. Your age is only a number. It doesn’t matter if you’re just out of college or your children are; we need you for what you can do. We strive to have parity of benefits across regions and while regulations differ from place to place, we believe taking care of our people is the right thing to do. Competitive pay based on the work you do here and not your previous salary Health coverage for you and your family in many locations Ability to craft your calendar with flexible locations and schedules for many roles Generous number of vacation days each year Increase your impact - We match up to $2000 (or local currency equivalent) for financial donations and service Up to 40 hours each year to use toward volunteer projects you love Embracing parenthood with minimum of 16 weeks of parental leave Different people approach problems differently. We need that. Elastic is an equal opportunity employer and is committed to creating an inclusive culture that celebrates different perspectives, experiences, and backgrounds. Qualified applicants will receive consideration for employment without regard to race, ethnicity, color, religion, sex, pregnancy, sexual orientation, gender perception or identity, national origin, age, marital status, protected veteran status, disability status, or any other basis protected by federal, state or local law, ordinance or regulation. We welcome individuals with disabilities and strive to create an accessible and inclusive experience for all individuals. To request an accommodation during the application or the recruiting process, please email candidate_accessibility@elastic.co. We will reply to your request within 24 business hours of submission. Applicants have rights under Federal Employment Laws, view posters linked below: Family and Medical Leave Act (FMLA) Poster; Pay Transparency Nondiscrimination Provision Poster; Employee Polygraph Protection Act (EPPA) Poster and Know Your Rights (Poster) Elasticsearch develops and distributes technology and information that is subject to U. S. and other countries’ export controls and licensing requirements for individuals who are located in or are nationals of the following sanctioned countries and regions: Belarus, Cuba, Iran, North Korea, Syria, or Russia, including the Ukrainian territories annexed by Russia (The Crimea region of Ukraine, The Donetsk People's Republic (DNR), The Luhansk People's Republic (LNR), Kherson or Zaporizhzhia). If you are located in or are a national of one of the listed countries or regions, an export license may be required as a condition of your employment in this role. Please note that national origin and/or nationality do not affect eligibility for employment with Elastic. Please see here for our Privacy Statement.", "summaryDescription" : "Senior Java Engineer - Distributed Systems - Elasticsearch at Elastic. Skills: Distributed systems, Elasticsearch, Java, Microservices. Design, build, and maintain scalable microservices. Develop and optimize Elasticsearch solutions", "postedDate" : "2026-06-14T19:17:58.197", "createdAt" : "2026-06-14T19:17:58.197", "lastUpdated" : "2026-06-16T06:54:33.374", "ingestTimestamp" : "2026-06-14T19:17:58.197", "mongoId" : "6a2c799674d8ee00a0941f6e", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ "Distributed systems", "Microservices architecture", "Cloud platforms", "Containerization", "Monitoring and alerting", "Performance optimization", "Security best practices", "Elasticsearch", "Java", "Microservices", "System design", "Performance tuning", "Agile methodologies", "Docker", "Kubernetes", "AWS", "GCP", "Azure", "CI/CD tools" ], "skillCount" : 19, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2c5f4074d8ee00a08ea54e", "title" : "Principal Observability Platform Engineer", "company" : "Nscale", "industry" : "Technology", "salary" : { "min" : 150000.0, "max" : 215000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : false }, "location" : "US", "locations" : [ "US" ], "timestamp" : "2026-06-15T00:16:00.194", "fingerprint" : "3016dc034a8fc4090b9ad945a6cf41e0b210e0d3fc26a10e6287f865a10e10df", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://job-boards.eu.greenhouse.io/nscaleoperationsukltd/jobs/4832871101", "externalId" : "4832871101", "industryFunction" : { }, "structuredLocations" : [ { "country" : "United States", "continent" : "na", "workMode" : "onsite" } ], "locationText" : "United States", "experienceMinYears" : 8, "experienceMaxYears" : 99, "experienceLevel" : "Principal", "technicalSkills" : "Python, Go, Kubernetes, Prometheus, Thanos, VictoriaMetrics, Grafana, Loki, Tempo, OpenTelemetry, ClickHouse, Elastic, Terraform, Ansible, Kafka, Vector, Fluent Bit", "professionalSkills" : [ "System design", "Technical strategy", "Architecture roadmap", "Engineering practices", "Product management", "Data modeling", "Cardinality management", "Signal quality", "Operational efficiency", "Scalability" ], "hardSkillsList" : [ "Observability platform", "GPU clusters", "AI workloads", "Infrastructure operations", "Metrics", "Logs", "Traces", "Alerting", "Ingestion patterns", "Retention", "Failure visibility", "Incident postmortems", "Platform improvements", "Tool evaluation", "Engineering fundamentals", "Complex systems", "Infrastructure-as-Code", "Streaming pipelines", "AI/ML infrastructure", "GPU utilisation", "Training job visibility", "Inference latency", "Organizational strategy" ], "softSkillsList" : [ "Ownership", "Accountability", "Excellence", "Urgency", "Openness", "Transparency", "Simplicity", "Mentoring" ], "hardSkills" : [ { "name" : "Observability platform", "level" : "intermediate" }, { "name" : "GPU clusters", "level" : "intermediate" }, { "name" : "AI workloads", "level" : "intermediate" }, { "name" : "Infrastructure operations", "level" : "intermediate" }, { "name" : "Metrics", "level" : "intermediate" }, { "name" : "Logs", "level" : "intermediate" }, { "name" : "Traces", "level" : "intermediate" }, { "name" : "Alerting", "level" : "intermediate" }, { "name" : "Ingestion patterns", "level" : "intermediate" }, { "name" : "Retention", "level" : "intermediate" }, { "name" : "Failure visibility", "level" : "intermediate" }, { "name" : "Incident postmortems", "level" : "intermediate" }, { "name" : "Platform improvements", "level" : "intermediate" }, { "name" : "Tool evaluation", "level" : "intermediate" }, { "name" : "Engineering fundamentals", "level" : "intermediate" }, { "name" : "Complex systems", "level" : "intermediate" }, { "name" : "Infrastructure-as-Code", "level" : "intermediate" }, { "name" : "Streaming pipelines", "level" : "intermediate" }, { "name" : "AI/ML infrastructure", "level" : "intermediate" }, { "name" : "GPU utilisation", "level" : "intermediate" }, { "name" : "Training job visibility", "level" : "intermediate" }, { "name" : "Inference latency", "level" : "intermediate" }, { "name" : "Organizational strategy", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Ownership" }, { "name" : "Accountability" }, { "name" : "Excellence" }, { "name" : "Urgency" }, { "name" : "Openness" }, { "name" : "Transparency" }, { "name" : "Simplicity" }, { "name" : "Mentoring" } ], "majorSkills" : "Observability platform, Platform engineering, Infrastructure engineering, AI/ML infrastructure", "majorSkillsList" : [ "Observability platform", "Platform engineering", "Infrastructure engineering", "AI/ML infrastructure" ], "coreResponsibilities" : "Own technical strategy for observability, Own architecture for observability, Drive platform decisions, Identify systemic gaps, Design platforms that make failure visible, Design platforms that make failure fast to diagnose, Partner with SRE teams, Partner with infrastructure teams, Partner with AI/ML teams, Embed observability natively, Define standards for engineers, Define patterns for engineers, Mentor observability team, Technically grow observability team, Lead incident postmortems, Use postmortems for platform improvements, Evaluate tooling, Introduce tooling, Retire tooling", "teamCollaboration" : "Partner with SRE; Partner with infrastructure; Partner with AI/ML teams", "projectManagementSkills" : [ "Technical strategy", "Architecture roadmap" ], "domainKnowledge" : "GPU cloud; AI infrastructure; Observability; HPC environments; AI/ML infrastructure observability", "domainList" : [ "gpu-cloud", "ai-infrastructure", "observability", "hpc-environments", "ai-ml-infrastructure-observability" ], "domainSpecificKnowledge" : [ "GPU cloud", "AI infrastructure", "Observability", "HPC environments", "AI/ML infrastructure observability" ], "toolProficiency" : [ "Prometheus", "Thanos", "VictoriaMetrics", "Grafana", "Loki", "Tempo", "OpenTelemetry", "ClickHouse", "Elastic", "Terraform", "Ansible", "Kafka", "Vector", "Fluent Bit", "Slurm" ], "communicationSkills" : "Explain tradeoffs clearly", "innovationCreativity" : "Relentless innovation", "problemSolvingSkills" : "Root cause analysis; Troubleshooting; Diagnose failures", "outcomesObjectives" : "Ensure platform scales ahead of business", "qualificationsBasic" : "8+ years in SRE, 8+ years in infrastructure engineering, 8+ years in platform engineering, 8+ years in observability-focused roles, Operated observability infrastructure at scale, Proficient in Python, Proficient in Go, Comfortable owning complex systems end to end, Infrastructure-as-Code is default, Influence without authority", "qualificationsPreferred" : "Familiarity with GPU infrastructure, Familiarity with HPC environments, Slurm familiarity, Experience with high-volume streaming pipelines, Background in AI/ML infrastructure observability, Prior experience defining observability strategy", "remoteFriendly" : false, "rawDescription" : "Principal Observability Platform Engineer – Nscale About Nscale Nscale is the GPU cloud engineered for AI. We provide cost-effective, high-performance infrastructure for AI start-ups and large enterprise customers. Nscale simplifies AI development while enabling superior results, supporting strategic business outcomes such as cost management, rapid innovation, and environmental responsibility. We thrive on a culture of relentless innovation, ownership, and accountability, where every team member takes pride in their work and drives it with excellence and urgency. As an Nscaler, you’ll build trust through openness and transparency while contributing to the technology that powers the future. About the Role As a Principal/Staff Observability Platform Engineer, you'll own the technical direction of Nscale's observability platform: the systems that give us deep visibility into GPU clusters, AI workloads, and the infrastructure running them. You treat observability as a product and a discipline, not a tooling exercise. You'll set the architectural roadmap, raise the engineering bar across teams, and ensure our platform scales ahead of the business, not behind it. You understand that complexity is a cost. Solutions that require constant babysitting don't scale, and neither does operational burden. The platforms you build should be simple to operate, easy to understand, and self-evidently correct when something goes wrong. This isn't a \"maintain and operate\" role. It's a \"define, build, and lead\" role. What You'll Do Own the technical strategy and architecture for observability across metrics, logs, traces, and alerting at scale. Drive platform decisions that have multi-year impact: tooling, data models, ingestion patterns, retention, cardinality management. Identify systemic gaps before they become incidents; design platforms that make failure visible and fast to diagnose. Partner with SRE, infrastructure, and AI/ML teams to embed observability natively into how Nscale builds and operates. Define standards and patterns that other engineers adopt, not by mandate, but because they're clearly better. Mentor and technically grow the observability team; raise the ceiling on what the team can build and own. Lead incident postmortems and use them to drive durable platform improvements. Evaluate and introduce tooling that meaningfully improves signal quality, operational efficiency, or scalability, and retire what doesn' t. About You 8+ years in SRE, infrastructure engineering, platform engineering, or observability-focused roles. You've operated observability infrastructure at serious scale. You know what breaks at 10x and you design for it. You have a strong bias toward simplicity. You've seen over-engineered observability stacks collapse under their own weight and you build accordingly. Deep hands-on experience with a significant subset of: Prometheus, Thanos, VictoriaMetrics, Grafana, Loki, Tempo, OpenTelemetry, ClickHouse, Elastic. Strong engineering fundamentals, proficient in Python, Go, or similar; comfortable owning complex systems end to end. Experience with Kubernetes at scale; familiarity with GPU infrastructure or HPC environments (Slurm) is a strong plus. You can architect systems, write the code, review others' work, and explain the tradeoffs clearly, all in the same week. Infrastructure-as-Code is default, not optional (Terraform, Ansible, or equivalent). You influence without authority. Teams want your opinion because it makes their work better. Preferred Experience with high-volume streaming pipelines for observability data (Kafka, Vector, Fluent Bit, etc.). Background in AI/ML infrastructure observability: GPU utilisation, training job visibility, inference latency. Prior experience defining observability strategy at an organisation level. Equal Opportunities Statement We strongly encourage applications from people of color, the LGBTQ+ community, people with disabilities, neurodivergent individuals, parents, carers, and people from lower socio-economic backgrounds. If there’s anything we can do to accommodate your specific situation, please let us know. Note: Responsibilities outlined are not exhaustive and may evolve as business needs change. The range below reflects the base salary for the position. Actual compensation may vary based on job-related factors such as skill set, experience, education, and location. In addition to base salary, this role may be eligible for bonus, equity, and/or commission programs. Nscale may offer a competitive benefits package including medical, dental, vision, flexible paid time off, parental leave, and retirement plan participation. Salary Range $150,000—$215,000 USD For information on how Nscale handles candidate personal data, please see our Employee & Candidate Privacy Notice: Here.", "summaryDescription" : "Principal Observability Platform Engineer at Nscale. Skills: Observability platform, Platform engineering, Infrastructure engineering, AI/ML infrastructure. Own technical strategy for observability. Own architecture for observability", "postedDate" : "2026-06-12T22:10:31.276", "createdAt" : "2026-06-12T22:10:31.276", "lastUpdated" : "2026-06-15T00:16:00.194", "ingestTimestamp" : "2026-06-12T22:10:31.276", "mongoId" : "6a2c5f4074d8ee00a08ea54e", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 150000, "salaryAnnualMax" : 215000, "salaryBand" : "150k-200k", "hasSalary" : true, "allSkills" : [ "Observability platform", "GPU clusters", "AI workloads", "Infrastructure operations", "Metrics", "Logs", "Traces", "Alerting", "Ingestion patterns", "Retention", "Failure visibility", "Incident postmortems", "Platform improvements", "Tool evaluation", "Engineering fundamentals", "Complex systems", "Infrastructure-as-Code", "Streaming pipelines", "AI/ML infrastructure", "GPU utilisation", "Training job visibility", "Inference latency", "Organizational strategy", "Ownership", "Accountability", "Excellence", "Urgency", "Openness", "Transparency", "Simplicity", "Mentoring", "Platform engineering", "Infrastructure engineering", "System design", "Technical strategy", "Architecture roadmap", "Engineering practices", "Product management", "Data modeling", "Cardinality management", "Signal quality", "Operational efficiency", "Scalability", "GPU cloud", "AI infrastructure", "Observability", "HPC environments", "AI/ML infrastructure observability", "Prometheus", "Thanos", "VictoriaMetrics", "Grafana", "Loki", "Tempo", "OpenTelemetry", "ClickHouse", "Elastic", "Terraform", "Ansible", "Kafka", "Vector", "Fluent Bit", "Slurm" ], "skillCount" : 63, "jobCategory" : "operations", "jobSubcategory" : "ai-infrastructure-operations", "dataQualityScore" : 0.8888889, "daysOld" : 2, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology" }, { "id" : "6a2c799674d8ee00a0941f72", "title" : "Senior Java Engineer - Distributed Systems - Elasticsearch", "company" : "Elastic", "industry" : "Technology", "salary" : { "min" : 4500000.0, "max" : 7500000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Java Engineer in the Technology industry, adjusted for seniority and global remote work." }, "location" : "Distributed, Global", "locations" : [ "Distributed", "Global" ], "timestamp" : "2026-06-16T01:38:19.252", "fingerprint" : "1c130fddb3c698ced4966ba6f053b5cd7ad42b358ee487999a8d93f3eaaac5cf", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://jobs.elastic.co/jobs?gh_jid=8001185&gh_jid=8001185", "externalId" : "8001185", "industryFunction" : { }, "structuredLocations" : [ { "workMode" : "remote" } ], "locationText" : "", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Java, Spring Boot, Kafka, Redis, Elasticsearch, Microservices, AWS, GCP, Azure, Docker, Kubernetes, SQL, NoSQL, CI/CD, Go, GRPC", "professionalSkills" : [ "System design", "Performance tuning", "Security best practices" ], "hardSkillsList" : [ "Distributed systems", "Microservices architecture", "Containerization", "Monitoring", "Alerting", "Performance optimization" ], "hardSkills" : [ { "name" : "Distributed systems", "level" : "intermediate" }, { "name" : "Microservices architecture", "level" : "intermediate" }, { "name" : "Containerization", "level" : "intermediate" }, { "name" : "Monitoring", "level" : "intermediate" }, { "name" : "Alerting", "level" : "intermediate" }, { "name" : "Performance optimization", "level" : "intermediate" } ], "majorSkills" : "Distributed systems, Elasticsearch, Java, Microservices", "majorSkillsList" : [ "Distributed systems", "Elasticsearch", "Java", "Microservices" ], "coreResponsibilities" : "Design, build, and maintain scalable distributed systems, Develop and optimize Elasticsearch solutions, Write high-quality, maintainable Java code, Implement and manage microservices architecture, Deploy and manage applications on cloud platforms, Build and maintain CI/CD pipelines, Containerize applications using Docker and Kubernetes, Work with SQL and NoSQL databases, Implement monitoring and alerting systems, Tune system performance and optimize resource utilization, Ensure security best practices are followed, Collaborate with cross-functional teams, Participate in code reviews, Troubleshoot and resolve production issues, Contribute to architectural decisions, Stay up-to-date with new technologies", "teamCollaboration" : "Cross-functional teams; Code reviews", "projectManagementSkills" : [ "Agile methodologies" ], "domainKnowledge" : "Distributed systems; Elasticsearch; Microservices architecture; Cloud platforms", "domainList" : [ "distributed-systems", "elasticsearch", "microservices-architecture", "cloud-platforms" ], "domainSpecificKnowledge" : [ "Distributed systems", "Elasticsearch", "Microservices architecture", "Cloud platforms" ], "toolProficiency" : [ "Docker", "Kubernetes", "AWS", "GCP", "Azure", "CI/CD tools" ], "problemSolvingSkills" : "Performance tuning; Optimization; Troubleshooting", "qualificationsBasic" : "5+ years of experience in software development, Experience with distributed systems, Experience with Elasticsearch, Experience with Java, Experience with Spring Boot, Experience with Kafka, Experience with Redis, Experience with microservices architecture, Experience with cloud platforms (AWS, GCP, Azure), Experience with CI/CD pipelines, Experience with containerization (Docker, Kubernetes), Experience with SQL and NoSQL databases, Experience with monitoring and alerting tools, Experience with performance tuning and optimization, Experience with security best practices, Experience with Agile methodologies", "qualificationsPreferred" : "Experience with Go, Experience with gRPC, Experience with distributed tracing, Experience with observability tools, Experience with data streaming platforms, Experience with machine learning frameworks, Master's degree in Computer Science or related field", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI. What Is The Role: We are on the lookout for a Senior Software Engineer to join our Elasticsearch - Distributed Systems team and focus on how Elasticsearch provides scale, performance, and resilience. This team owns how nodes in an Elasticsearch cluster communicate, and how data are indexed, allocated, and replicated across nodes. What You Will Be Doing: Improving Elasticsearch’s components that support concurrent and consistent indexing across multiple machines. Maintaining our cluster coordination system to keep performance high even though nodes come and go from the cluster and data moves around, while maintaining the safety and liveness properties of the system as a whole. Pushing the limits on the number of shards, nodes, and petabytes that Elasticsearch can handle today Looking into all kinds of issues, including performance or concurrency issues, and proposing solutions. Supporting our support engineers with the harder problems. What You Bring: A strong background in distributed systems and consensus algorithms. You have strong skills in core Java and are conversant in the standard library of data structures and concurrency constructs, as well as newer language features. You have a deep technical proficiency in algorithms. You have shown your ability to understand and work on complex, highly distributed systems. You demonstrate the ability to build and debug features with a broad impact, running on multiple machines. You are able to own projects from beginning to end. This covers both technical design and working with others to develop needed components. Bonus Points: Data stores Search, analytics, Lucene Strong knowledge of the JDK Asynchronous event-driven network frameworks such as Netty Compensation for this role is in the form of base salary. This role does not have a variable compensation component. At Elastic, our compensation philosophy aims to provide fair, competitive and transparent remuneration. Salary ranges are established based on a combination of external market benchmarks, internal pay equity considerations, and the responsibilities and complexity associated with each role. This approach helps ensure consistency across comparable roles while remaining competitive within the relevant labour markets. The final compensation offered within the applicable range will be determined based on several objective factors, including relevant professional experience, level of skills and expertise, alignment with the role requirements, and the overall scope and complexity of the position. The typical starting salary range for this role is: 15 805 300 Ft—25 001 600 Ft HUF Additional Information - We Take Care of Our People As a distributed company, diversity drives our identity. Whether you’re looking to launch a new career or grow an existing one, Elastic is the type of company where you can balance great work with great life. Your age is only a number. It doesn’t matter if you’re just out of college or your children are; we need you for what you can do. We strive to have parity of benefits across regions and while regulations differ from place to place, we believe taking care of our people is the right thing to do. Competitive pay based on the work you do here and not your previous salary Health coverage for you and your family in many locations Ability to craft your calendar with flexible locations and schedules for many roles Generous number of vacation days each year Increase your impact - We match up to $2000 (or local currency equivalent) for financial donations and service Up to 40 hours each year to use toward volunteer projects you love Embracing parenthood with minimum of 16 weeks of parental leave Different people approach problems differently. We need that. Elastic is an equal opportunity employer and is committed to creating an inclusive culture that celebrates different perspectives, experiences, and backgrounds. Qualified applicants will receive consideration for employment without regard to race, ethnicity, color, religion, sex, pregnancy, sexual orientation, gender perception or identity, national origin, age, marital status, protected veteran status, disability status, or any other basis protected by federal, state or local law, ordinance or regulation. We welcome individuals with disabilities and strive to create an accessible and inclusive experience for all individuals. To request an accommodation during the application or the recruiting process, please email candidate_accessibility@elastic.co. We will reply to your request within 24 business hours of submission. Applicants have rights under Federal Employment Laws, view posters linked below: Family and Medical Leave Act (FMLA) Poster; Pay Transparency Nondiscrimination Provision Poster; Employee Polygraph Protection Act (EPPA) Poster and Know Your Rights (Poster) Elasticsearch develops and distributes technology and information that is subject to U. S. and other countries’ export controls and licensing requirements for individuals who are located in or are nationals of the following sanctioned countries and regions: Belarus, Cuba, Iran, North Korea, Syria, or Russia, including the Ukrainian territories annexed by Russia (The Crimea region of Ukraine, The Donetsk People's Republic (DNR), The Luhansk People's Republic (LNR), Kherson or Zaporizhzhia). If you are located in or are a national of one of the listed countries or regions, an export license may be required as a condition of your employment in this role. Please note that national origin and/or nationality do not affect eligibility for employment with Elastic. Please see here for our Privacy Statement.", "summaryDescription" : "Senior Java Engineer - Distributed Systems - Elasticsearch at Elastic. Skills: Distributed systems, Elasticsearch, Java, Microservices. Design, build, and maintain scalable distributed systems. Develop and optimize Elasticsearch solutions", "postedDate" : "2026-06-14T18:40:13.624", "createdAt" : "2026-06-14T18:40:13.624", "lastUpdated" : "2026-06-16T01:38:19.252", "ingestTimestamp" : "2026-06-14T18:40:13.624", "mongoId" : "6a2c799674d8ee00a0941f72", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ "Distributed systems", "Microservices architecture", "Containerization", "Monitoring", "Alerting", "Performance optimization", "Elasticsearch", "Java", "Microservices", "System design", "Performance tuning", "Security best practices", "Agile methodologies", "Cloud platforms", "Docker", "Kubernetes", "AWS", "GCP", "Azure", "CI/CD tools" ], "skillCount" : 20, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2a670b74d8ee00a062e377", "title" : "Senior Observability Lead", "company" : "Johnson Controls", "industry" : "Building Automation", "salary" : { "min" : 2500000.0, "max" : 4000000.0, "currency" : "INR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Observability Lead in Mumbai, India, adjusted for lead seniority and the technology industry." }, "location" : "Mumbai-Maharashtra-India", "locations" : [ "Mumbai-Maharashtra-India" ], "timestamp" : "2026-06-13T18:38:30.821", "fingerprint" : "24e657f7a33da493107e6b6b773cc58f50f611182905a630810d89ff2afc3b25", "source" : "workday", "language" : "en", "applyUrl" : "https://jci.wd5.myworkdayjobs.com/JCI/job/Mumbai-Maharashtra-India/Senior-Software-Engineer---SRE_WD30271552", "externalId" : "WD30271552", "industryFunction" : { }, "locationPoint" : "19.07283,72.88261", "structuredLocations" : [ { "city" : "Mumbai", "state" : "Maharashtra", "country" : "India", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "19.0549990,72.8692035" } ], "locationText" : "Mumbai, Maharashtra, India", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Grafana Cloud, Datadog, Dynatrace, ELK, Logz.io, OpenTelemetry, Azure, AWS, GCP, Kubernetes, Linux, Windows, SQL", "professionalSkills" : [ "Technical leadership", "Observability strategy", "Platform optimization", "Service reliability", "Incident response", "ITIL process" ], "hardSkillsList" : [ "Metrics", "Logs", "Traces", "Infrastructure as Code", "APIs", "CI/CD pipelines", "Application event flows" ], "softSkillsList" : [ "Leadership" ], "hardSkills" : [ { "name" : "Metrics", "level" : "intermediate" }, { "name" : "Logs", "level" : "intermediate" }, { "name" : "Traces", "level" : "intermediate" }, { "name" : "Infrastructure as Code", "level" : "intermediate" }, { "name" : "APIs", "level" : "intermediate" }, { "name" : "CI/CD pipelines", "level" : "intermediate" }, { "name" : "Application event flows", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Leadership" } ], "majorSkills" : "Observability, Grafana Cloud, SRE, Site Reliability Engineering", "majorSkillsList" : [ "Observability", "Grafana Cloud", "SRE", "Site Reliability Engineering" ], "coreResponsibilities" : "Lead observability strategy, Define observability standards, Improve telemetry quality, Automate platform provisioning, Implement SLIs, SLOs, SLAs, Implement error budgets, Improve reliability, Reduce alert noise, Support faster incident response, Design observability solutions, Build observability solutions, Manage observability solutions, Own Grafana Cloud architecture, Optimize Grafana Cloud, Drive platform consolidation, Support existing Datadog environments, Support Datadog, Support Dynatrace, Support log management platforms, Develop monitoring strategies, Develop alerting strategies, Automate observability platform provisioning, Automate integrations, Partner with application teams, Partner with SRE teams, Partner with DevOps teams, Improve instrumentation, Provide L3 support, Troubleshoot incidents, Perform root cause analysis, Ensure compliance with security standards, Ensure compliance with operational standards, Ensure compliance with ITIL process standards, Maintain documentation, Share knowledge, Mentor teams", "teamCollaboration" : "Global engineering teams; Application teams; SRE teams; DevOps teams", "projectManagementSkills" : [ "Platform transformation" ], "domainKnowledge" : "Distributed systems; Cloud platforms; Kubernetes; Containers; Linux; Windows; Databases; SQL; Application event flows; Observability; Metrics; Logs; Traces; OpenTelemetry; SLIs; SLOs; SLAs; Error budgets; Infrastructure as Code; APIs; CI/CD pipelines; ITIL process", "domainList" : [ "distributed-systems", "cloud-platforms", "kubernetes", "containers", "linux", "windows", "databases", "sql", "application-event-flows", "observability", "metrics", "logs", "traces", "opentelemetry", "slis", "slos", "slas", "error-budgets", "infrastructure-as-code", "apis", "ci-cd-pipelines", "itil-process" ], "domainSpecificKnowledge" : [ "Distributed systems", "Cloud platforms", "Kubernetes", "Containers", "Linux", "Windows", "Databases", "SQL", "Application event flows", "Observability", "Metrics", "Logs", "Traces", "OpenTelemetry", "SLIs", "SLOs", "SLAs", "Error budgets", "Infrastructure as Code", "APIs", "CI/CD pipelines", "ITIL process" ], "toolProficiency" : [ "Grafana Cloud", "Datadog", "Dynatrace", "ELK", "Logz.io", "Kubernetes" ], "documentationSkills" : "Maintain documentation", "problemSolvingSkills" : "Troubleshooting; Root cause analysis", "outcomesObjectives" : "Improve service reliability; Reduce alert noise; Support faster incident response", "qualificationsBasic" : "8+ years of experience in SRE, observability, or monitoring engineering, Bachelor’s degree in computer science, Information Systems, or a related technical field, Expert-level experience with Grafana Cloud, Hands-on experience with Datadog or Dynatrace, Experience with log management tools such as ELK or Logz.io, Experience implementing SLIs, SLOs, SLAs, and error budgets, Hands-on experience with observability automation using Infrastructure as Code, APIs, or CI/CD pipelines, Understanding of metrics, logs, traces, OpenTelemetry, and distributed system observability, Experience with cloud platforms such as Azure, AWS, and GCP, Experience with Kubernetes and containers, Good knowledge of Linux, Windows, databases, SQL, and application event flows", "qualificationsPreferred" : "Support for platform transformation initiatives", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "Job Description Johnson Controls is the global leader for smart, healthy and sustainable buildings. At Johnson Controls, we’ve been making buildings smarter since 1885, and our capabilities, depth of innovation experience, and global reach have been growing ever since. Today, we offer the world’s largest portfolio of building products, technologies, software, and services; we put that portfolio to work to transform the environments where people live, work, learn and play. This is where Johnson Controls comes in, helping drive the outcomes that matter most. Through a full range of systems and digital solutions, we make your buildings smarter. A smarter building is safer, more comfortable, more efficient, and, ultimately, more sustainable. Most important, smarter buildings let you focus more intensely on your unique mission. Better for your people. Better for your bottom line. Better for the planet. We’re helping to create a healthy planet with solutions that decrease energy use, reduce waste and make carbon neutrality a reality. Sustainability is a top priority for our company. We committed to invest 75 percent of new product development R&D in climate-related innovation to develop sustainable products and services. We take sustainability seriously. Achieving net zero carbon emissions before 2040 is just one of our commitments to making the world a better place. Please visit and follow Johnson Controls LinkedIn for recent exciting activities. Why JCI: https://www.youtube.com/watch?v=nrbigjbpxkg Asia-Pacific LinkedIn: https://www.linkedin.com/showcase/johnson-controls-asia-pacific/posts/?feedView=all Career: The Power Behind Your Mission OpenBlue: This is How a Space Comes ALive **Job Summary** The Site Reliability Engineering team at Johnson Controls is seeking a Senior Observability Lead to build, automate, and lead a modern observability platform across applications and infrastructure. This role will own Grafana Cloud end-to-end and drive the transformation and consolidation of observability platforms onto Grafana Cloud while supporting existing Datadog environments. The role will define observability standards, improve telemetry quality, automate platform provisioning, and implement SLIs, SLOs, SLAs, and error budgets to improve reliability, reduce alert noise, and support faster incident response across global engineering teams **Key Responsibilities** * Lead observability strategy, standards, and best practices across engineering teams * Design, build, and manage observability solutions across metrics, logs, traces, dashboards, and alerting * Own Grafana Cloud architecture, setup, administration, and optimization across key platform components * Drive the transformation and consolidation of observability platforms onto Grafana Cloud while maintaining and supporting existing Datadog environments * Support Datadog, Dynatrace, and log management platforms such as ELK or Logz.io as needed * Define and implement SLIs, SLOs, SLAs, and error budgets to improve service reliability * Develop monitoring and alerting strategies that reduce noise and improve signal quality * Automate observability platform provisioning and integrations using Infrastructure as Code, APIs, and CI/CD pipelines * Partner with application, SRE, and DevOps teams to improve instrumentation, telemetry quality, and OpenTelemetry adoption * Provide L3 support for incidents, troubleshooting, and root cause analysis * Ensure compliance with security, operational, and ITIL process standards * Maintain documentation, share knowledge, and mentor teams on observability practices **Required Skills & Qualifications** * 8+ years of experience in SRE, observability, or monitoring engineering * Bachelor’s degree in computer science, Information Systems, or a related technical field * Expert-level experience with Grafana Cloud, including setup, administration, and optimization * Hands-on experience with Datadog or Dynatrace and support for platform transformation initiatives * Experience with log management tools such as ELK or Logz.io * Strong experience implementing SLIs, SLOs, SLAs, and error budgets * Hands-on experience with observability automation using Infrastructure as Code, APIs, or CI/CD pipelines * Strong understanding of metrics, logs, traces, OpenTelemetry, and distributed system observability * Experience with cloud platforms such as Azure, AWS, and GCP, along with Kubernetes and containers * Good knowledge of Linux, Windows, databases, SQL, and application event flows to understand what should be monitored and instrumented * Strong communication, collaboration, and technical leadership skills across global teams **What We Offer** We offer an exciting and challenging position. Joining us you will become part of a leading global multi-industrial corporation defined by its stimulating work environment and job satisfaction. In addition, we offer outstanding career development opportunities which will stretch your abilities and channel your talents Industry-leading Building Automation platforms, Large-scale, mission-critical systems exposure, Global architecture and platform collaboration, Career growth in system architecture, protocol engineering, and platform design.", "summaryDescription" : "Senior Observability Lead at Johnson Controls. Skills: Observability, Grafana Cloud, SRE, Site Reliability Engineering. Lead observability strategy. Define observability standards", "postedDate" : "2026-06-11T16:43:25.091", "createdAt" : "2026-06-11T16:43:24.987", "lastUpdated" : "2026-06-13T18:38:30.821", "ingestTimestamp" : "2026-06-11T16:43:24.987", "mongoId" : "6a2a670b74d8ee00a062e377", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "sourceUrl" : "https://jci.wd5.myworkdayjobs.com/JCI/job/Mumbai-Maharashtra-India/Senior-Software-Engineer---SRE_WD30271552", "salaryBand" : "200k+", "hasSalary" : false, "allSkills" : [ "Metrics", "Logs", "Traces", "Infrastructure as Code", "APIs", "CI/CD pipelines", "Application event flows", "Leadership", "Observability", "Grafana Cloud", "SRE", "Site Reliability Engineering", "Technical leadership", "Observability strategy", "Platform optimization", "Service reliability", "Incident response", "ITIL process", "Platform transformation", "Distributed systems", "Cloud platforms", "Kubernetes", "Containers", "Linux", "Windows", "Databases", "SQL", "OpenTelemetry", "SLIs", "SLOs", "SLAs", "Error budgets", "Datadog", "Dynatrace", "ELK", "Logz.io" ], "skillCount" : 36, "jobCategory" : "engineering", "seniorityLevel" : "senior", "dataQualityScore" : 1.0, "daysOld" : 2, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Building Automation" }, { "id" : "6a2c7f2c74d8ee00a0954a54", "title" : "Senior Software Engineer - Observability Visibility", "company" : "Datadog", "industry" : "Technology", "salary" : { "min" : 175000.0, "max" : 250000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Senior Software Engineer in New York, adjusted for Datadog's size and industry, reflecting 2024-2025 data." }, "location" : "New York, NY, United States", "locations" : [ "New York", "NY", "United States" ], "timestamp" : "2026-06-15T06:35:27.285", "fingerprint" : "6014c13860bd6126ce935139fd1bf2de8a3649e425a8b4cbcbd249629f9c66fd", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://careers.datadoghq.com/detail/8001760/?gh_jid=8001760", "externalId" : "8001760", "industryFunction" : { }, "structuredLocations" : [ { "city" : "New York", "state" : "New York", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "hybrid", "geo" : "40.7127281,-74.0060152" } ], "locationText" : "New York, New York, United States", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Go, Python, AI-driven solutions", "professionalSkills" : [ "Technical leadership", "Problem-solving", "System design" ], "hardSkillsList" : [ "Service failure modes", "System failure modes" ], "softSkillsList" : [ "Mentoring" ], "hardSkills" : [ { "name" : "Service failure modes", "level" : "intermediate" }, { "name" : "System failure modes", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Mentoring" } ], "majorSkills" : "Observability, Resilience, Software engineering, Site reliability engineering", "majorSkillsList" : [ "Observability", "Resilience", "Software engineering", "Site reliability engineering" ], "coreResponsibilities" : "Define observability baselines, Evolve observability baselines, Define resilience baselines, Evolve resilience baselines, Measure service compliance, Assess risk, Assess remediation complexity, Drive sustainable solutions, Design scalable observability capabilities, Deliver scalable observability capabilities, Design scalable reliability capabilities, Deliver scalable reliability capabilities, Leverage automation, Leverage AI-driven solutions, Enable service owners, Partner with platform teams, Partner with SRE teams, Partner with product teams, Partner with engineering teams, Provide technical leadership, Coach team members, Accelerate team growth, Conduct design reviews, Collaborative problem-solving, Promote operational excellence", "teamCollaboration" : "SRE teams; Platform teams; Product teams; Engineering teams; Cross-functional teams", "domainKnowledge" : "Observability; Resilience; Service reliability; AI in software", "domainList" : [ "observability", "resilience", "service-reliability", "ai-in-software" ], "domainSpecificKnowledge" : [ "Observability", "Resilience", "Service reliability", "AI in software" ], "communicationSkills" : "Technical direction", "continuousLearning" : "Product training; Career pathing; Mentor program; Buddy program; In-house learning", "innovationCreativity" : "AI-driven solutions", "problemSolvingSkills" : "Root cause analysis; Troubleshooting", "outcomesObjectives" : "Reduce operational risk; Drive adoption; Drive consistency; Improve engineering effectiveness; Improve service resilience", "qualificationsBasic" : "5+ years experience software engineering, 5+ years experience site reliability engineering, Hands-on experience observability, Hands-on experience resilience, Expertise identifying failure modes, Expertise analyzing failure modes, Expertise mitigating failure modes, Programming skills in Go, Programming skills in Python, Design reliable systems, Build reliable systems, Design maintainable systems, Build maintainable systems, Navigating complex technical challenges, Proposing efficient solutions, Proposing scalable solutions, Proposing easy-to-adopt solutions, Experience delivering AI-enabled software, Articulate when AI is appropriate, Communication skills, Collaboration skills, Mentorship skills", "qualificationsPreferred" : "Experience influencing technical direction", "remoteFriendly" : true, "workSiteFlexibility" : "Hybrid", "rawDescription" : "The Observability Visibility SRE Team is part of the Observability and Resilience Enablement group within the SRE/Security organization. Observability and Resilience Enablement focuses on closing the loop between how Datadog engineers detect and respond to issues and incidents and how those learnings translate into measurable risk reduction and lower customer impact. The Observability Visibility team carries the organization's 100% visibility priority, defining observability and reliability baselines and ensuring services consistently meet them by default through scalable, automated, and sustainable solutions. As a Senior Software Engineer on this team, you will help define, implement and evolve observability and resilience standards across Datadog's engineering organization. You will build systems, tooling, libraries, and automation that make observability and reliability the default experience for service owners, reducing operational risk while driving adoption and consistency. This role combines software engineering and site reliability engineering to drive measurable improvements in engineering effectiveness and service resilience. You will work closely with SRE, platform and product teams to identify gaps, deliver scalable solutions and ensure long-term coverage and compliance with established standards. At Datadog, we place value in our office culture - the relationships and collaboration it builds and the creativity it brings to the table. We operate as a hybrid workplace to ensure our Datadogs can create a work-life harmony that best fits them. What You'll Do: Define and evolve observability and resilience baselines, ensuring alignment with measurable risk reduction goals across Datadog services. Measure service compliance against established standards, assess risk and remediation complexity and drive sustainable solutions to close identified gaps. Design and deliver scalable observability and reliability capabilities across the software development lifecycle, leveraging automation and AI-driven solutions where appropriate to enable service owners to meet established standards by default while partnering closely with platform, SRE, product and engineering teams to ensure adoption and sustained coverage. Provide technical leadership and day-to-day coaching to team members, accelerating their growth through design reviews, collaborative problem-solving and operational excellence best practices. Who You Are: You have 5+ years of experience in software engineering, site reliability engineering, or a related discipline supporting production systems at scale. You have hands-on experience with observability and resilience practices, including expertise in identifying, analyzing, and mitigating service and system failure modes. You have strong programming skills in Go and/or Python and can design and build reliable, maintainable systems. You are comfortable navigating complex technical challenges and proposing efficient, scalable, and easy-to-adopt solutions. You have experience delivering AI-enabled software features end-to-end, including design, evaluation, deployment and monitoring and can articulate when AI is the appropriate solution and when it is not. You have strong communication, collaboration, and mentorship skills with experience influencing technical direction across multiple engineering teams. Datadog values people from all walks of life. We know not everyone will meet all the above qualifications on day one. That’s okay. If you’re passionate about technology and want to grow your experience, we encourage you to apply. Benefits and Growth: New hire stock equity (RSUs) and employee stock purchase plan (ESPP) Continuous professional development, product training, and career pathing Intradepartmental mentor and buddy program for in-house networking An inclusive company culture and opportunities to participate in Community Guilds (Datadog employee resource groups) Access to Inclusion Talks and internal learning opportunities Free, global mental health benefits for employees and dependents age 6+ Competitive global benefits Benefits and Growth listed above may vary based on the country of your employment and the nature of your employment with Datadog. To conform to US export control regulations, candidates should be eligible for any required authorizations from the US government. This job is available in various departments within our company; to conform to US export control regulations, some of these roles may require candidates to be eligible for any required authorizations from the US government. #LI-Hybrid Datadog offers a competitive salary and equity package, and may include variable compensation. Actual compensation is based on factors such as the candidate's skills, qualifications, and experience. In addition, Datadog offers a wide range of best in class, comprehensive and inclusive employee benefits for this role including healthcare, dental, parental planning, and mental health benefits, a 401(k) plan and match, paid time off, fitness reimbursements, and a discounted employee stock purchase plan. The reasonably estimated yearly salary for this role at Datadog is: $175,000—$240,000 USD About Datadog: Datadog is the leading observability and security platform for the AI era, providing businesses with unified visibility across the technology stack to manage complexity at scale. It brings applications, infrastructure, data, models, and security into one place, using AI to detect and resolve issues before they impact customers. Trusted globally by Fortune 500 companies and high-growth AI leaders, Datadog enables businesses to move faster with clarity and confidence. Learn more about #DatadogLife on Instagram, LinkedIn, and Datadog Learning Center. Equal Opportunity at Datadog: Datadog is proud to offer equal employment opportunity to everyone regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, veteran status, and other characteristics protected by law. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. Here are our Candidate Legal Notices for your reference. Datadog endeavors to make our Careers Page accessible to all users. If you would like to contact us regarding the accessibility of our website or need assistance completing the application process, please complete this form. This form is for accommodation requests only and cannot be used to inquire about the status of applications. Privacy and AI Guidelines: Any information you submit to Datadog as part of your application will be processed in accordance with Datadog’s Applicant and Candidate Privacy Notice. For information on our AI policy, please visit Interviewing at Datadog AI Guidelines.", "summaryDescription" : "Senior Software Engineer - Observability Visibility at Datadog. Skills: Observability, Resilience, Software engineering, Site reliability engineering. Define observability baselines. Evolve observability baselines", "postedDate" : "2026-06-13T21:18:48.371", "createdAt" : "2026-06-13T21:18:48.371", "lastUpdated" : "2026-06-15T06:35:27.285", "ingestTimestamp" : "2026-06-13T21:18:48.371", "mongoId" : "6a2c7f2c74d8ee00a0954a54", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 175000, "salaryAnnualMax" : 250000, "salaryBand" : "150k-200k", "hasSalary" : true, "allSkills" : [ "Service failure modes", "System failure modes", "Mentoring", "Observability", "Resilience", "Software engineering", "Site reliability engineering", "Technical leadership", "Problem-solving", "System design", "Service reliability", "AI in software" ], "skillCount" : 12, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2c799474d8ee00a0941f0c", "title" : "Principal Software Engineer - Distributed Systems - Elasticsearch", "company" : "Elastic", "industry" : "Technology", "salary" : { "min" : 1.0E7, "max" : 1.8E7, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "The estimation is based on the market baseline for Principal Software Engineers in the Technology industry, adjusted for executive seniority, remote work, and a global distribution, reflecting 2024-2025 data." }, "location" : "Distributed, Global", "locations" : [ "Distributed", "Global" ], "timestamp" : "2026-06-16T00:59:41.314", "fingerprint" : "fb5db353edf8b1ac19f227af51de0bf7f25b030e17919ebd1844a9a03be16631", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://jobs.elastic.co/jobs?gh_jid=8002555&gh_jid=8002555", "externalId" : "8002555", "industryFunction" : { }, "structuredLocations" : [ { "workMode" : "remote" } ], "locationText" : "", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI. What Is The Role: We are on the lookout for a Principal Software Engineer I to join our Elasticsearch - Distributed Systems team and focus on how Elasticsearch provides scale, performance, and resilience. This team owns how nodes in an Elasticsearch cluster communicate, and how data are indexed, allocated, and replicated across nodes. What You Will Be Doing: Improving Elasticsearch’s components that support concurrent and consistent indexing across multiple machines. Maintaining our cluster coordination system to keep performance high even though nodes come and go from the cluster and data moves around, while maintaining the safety and liveness properties of the system as a whole. Pushing the limits on the number of shards, nodes, and petabytes that Elasticsearch can handle today Looking into all kinds of issues, including performance or concurrency issues, and proposing solutions. Supporting our support engineers with the harder problems. What You Bring: A strong background in distributed systems and consensus algorithms. You have strong skills in core Java and are conversant in the standard library of data structures and concurrency constructs, as well as newer language features. You have a deep technical proficiency in algorithms. You have shown your ability to understand and work on complex, highly distributed systems. You demonstrate the ability to build and debug features with a broad impact, running on multiple machines. You are able to own projects from beginning to end. This covers both technical design and working with others to develop needed components. You have experience managing projects involving multiple engineers. Bonus Points: Data stores Search, analytics, Lucene Strong knowledge of the JDK Asynchronous event-driven network frameworks such as Netty Compensation for this role is in the form of base salary. This role does not have a variable compensation component. At Elastic, our compensation philosophy aims to provide fair, competitive and transparent remuneration. Salary ranges are established based on a combination of external market benchmarks, internal pay equity considerations, and the responsibilities and complexity associated with each role. This approach helps ensure consistency across comparable roles while remaining competitive within the relevant labour markets. The final compensation offered within the applicable range will be determined based on several objective factors, including relevant professional experience, level of skills and expertise, alignment with the role requirements, and the overall scope and complexity of the position. The typical starting salary range for this role is: €73.300—€115.900 EUR Additional Information - We Take Care of Our People As a distributed company, diversity drives our identity. Whether you’re looking to launch a new career or grow an existing one, Elastic is the type of company where you can balance great work with great life. Your age is only a number. It doesn’t matter if you’re just out of college or your children are; we need you for what you can do. We strive to have parity of benefits across regions and while regulations differ from place to place, we believe taking care of our people is the right thing to do. Competitive pay based on the work you do here and not your previous salary Health coverage for you and your family in many locations Ability to craft your calendar with flexible locations and schedules for many roles Generous number of vacation days each year Increase your impact - We match up to $2000 (or local currency equivalent) for financial donations and service Up to 40 hours each year to use toward volunteer projects you love Embracing parenthood with minimum of 16 weeks of parental leave Different people approach problems differently. We need that. Elastic is an equal opportunity employer and is committed to creating an inclusive culture that celebrates different perspectives, experiences, and backgrounds. Qualified applicants will receive consideration for employment without regard to race, ethnicity, color, religion, sex, pregnancy, sexual orientation, gender perception or identity, national origin, age, marital status, protected veteran status, disability status, or any other basis protected by federal, state or local law, ordinance or regulation. We welcome individuals with disabilities and strive to create an accessible and inclusive experience for all individuals. To request an accommodation during the application or the recruiting process, please email candidate_accessibility@elastic.co. We will reply to your request within 24 business hours of submission. Applicants have rights under Federal Employment Laws, view posters linked below: Family and Medical Leave Act (FMLA) Poster; Pay Transparency Nondiscrimination Provision Poster; Employee Polygraph Protection Act (EPPA) Poster and Know Your Rights (Poster) Elasticsearch develops and distributes technology and information that is subject to U. S. and other countries’ export controls and licensing requirements for individuals who are located in or are nationals of the following sanctioned countries and regions: Belarus, Cuba, Iran, North Korea, Syria, or Russia, including the Ukrainian territories annexed by Russia (The Crimea region of Ukraine, The Donetsk People's Republic (DNR), The Luhansk People's Republic (LNR), Kherson or Zaporizhzhia). If you are located in or are a national of one of the listed countries or regions, an export license may be required as a condition of your employment in this role. Please note that national origin and/or nationality do not affect eligibility for employment with Elastic. Please see here for our Privacy Statement.", "summaryDescription" : "Principal Software Engineer - Distributed Systems - Elasticsearch at Elastic", "postedDate" : "2026-06-14T21:29:13.847", "createdAt" : "2026-06-14T21:29:13.847", "lastUpdated" : "2026-06-16T00:59:41.314", "ingestTimestamp" : "2026-06-14T21:29:13.847", "mongoId" : "6a2c799474d8ee00a0941f0c", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 10000000, "salaryAnnualMax" : 18000000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Executive", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2c799474d8ee00a0941f11", "title" : "Principal Software Engineer - Distributed Systems - Elasticsearch", "company" : "Elastic", "industry" : "Technology", "salary" : { "min" : 1.0E7, "max" : 1.8E7, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "The estimation is based on the market baseline for Principal Software Engineers in the Technology industry, adjusted for executive seniority, remote work, and the global nature of the role." }, "location" : "Distributed, Global", "locations" : [ "Distributed", "Global" ], "timestamp" : "2026-06-16T01:04:03.979", "fingerprint" : "0bd3d2943d9b49615394d694bab25e30bae1c2cdebeda84602cbb69ae3856a8c", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://jobs.elastic.co/jobs?gh_jid=8002563&gh_jid=8002563", "externalId" : "8002563", "industryFunction" : { }, "structuredLocations" : [ { "workMode" : "remote" } ], "locationText" : "", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI. What Is The Role: We are on the lookout for a Principal Software Engineer I to join our Elasticsearch - Distributed Systems team and focus on how Elasticsearch provides scale, performance, and resilience. This team owns how nodes in an Elasticsearch cluster communicate, and how data are indexed, allocated, and replicated across nodes. What You Will Be Doing: Improving Elasticsearch’s components that support concurrent and consistent indexing across multiple machines. Maintaining our cluster coordination system to keep performance high even though nodes come and go from the cluster and data moves around, while maintaining the safety and liveness properties of the system as a whole. Pushing the limits on the number of shards, nodes, and petabytes that Elasticsearch can handle today Looking into all kinds of issues, including performance or concurrency issues, and proposing solutions. Supporting our support engineers with the harder problems. What You Bring: A strong background in distributed systems and consensus algorithms. You have strong skills in core Java and are conversant in the standard library of data structures and concurrency constructs, as well as newer language features. You have a deep technical proficiency in algorithms. You have shown your ability to understand and work on complex, highly distributed systems. You demonstrate the ability to build and debug features with a broad impact, running on multiple machines. You are able to own projects from beginning to end. This covers both technical design and working with others to develop needed components. You have experience managing projects involving multiple engineers. Bonus Points: Data stores Search, analytics, Lucene Strong knowledge of the JDK Asynchronous event-driven network frameworks such as Netty Compensation for this role is in the form of base salary. This role does not have a variable compensation component. At Elastic, our compensation philosophy aims to provide fair, competitive and transparent remuneration. Salary ranges are established based on a combination of external market benchmarks, internal pay equity considerations, and the responsibilities and complexity associated with each role. This approach helps ensure consistency across comparable roles while remaining competitive within the relevant labour markets. The final compensation offered within the applicable range will be determined based on several objective factors, including relevant professional experience, level of skills and expertise, alignment with the role requirements, and the overall scope and complexity of the position. The typical starting salary range for this role is: 831 700 kr—1 315 600 kr SEK Additional Information - We Take Care of Our People As a distributed company, diversity drives our identity. Whether you’re looking to launch a new career or grow an existing one, Elastic is the type of company where you can balance great work with great life. Your age is only a number. It doesn’t matter if you’re just out of college or your children are; we need you for what you can do. We strive to have parity of benefits across regions and while regulations differ from place to place, we believe taking care of our people is the right thing to do. Competitive pay based on the work you do here and not your previous salary Health coverage for you and your family in many locations Ability to craft your calendar with flexible locations and schedules for many roles Generous number of vacation days each year Increase your impact - We match up to $2000 (or local currency equivalent) for financial donations and service Up to 40 hours each year to use toward volunteer projects you love Embracing parenthood with minimum of 16 weeks of parental leave Different people approach problems differently. We need that. Elastic is an equal opportunity employer and is committed to creating an inclusive culture that celebrates different perspectives, experiences, and backgrounds. Qualified applicants will receive consideration for employment without regard to race, ethnicity, color, religion, sex, pregnancy, sexual orientation, gender perception or identity, national origin, age, marital status, protected veteran status, disability status, or any other basis protected by federal, state or local law, ordinance or regulation. We welcome individuals with disabilities and strive to create an accessible and inclusive experience for all individuals. To request an accommodation during the application or the recruiting process, please email candidate_accessibility@elastic.co. We will reply to your request within 24 business hours of submission. Applicants have rights under Federal Employment Laws, view posters linked below: Family and Medical Leave Act (FMLA) Poster; Pay Transparency Nondiscrimination Provision Poster; Employee Polygraph Protection Act (EPPA) Poster and Know Your Rights (Poster) Elasticsearch develops and distributes technology and information that is subject to U. S. and other countries’ export controls and licensing requirements for individuals who are located in or are nationals of the following sanctioned countries and regions: Belarus, Cuba, Iran, North Korea, Syria, or Russia, including the Ukrainian territories annexed by Russia (The Crimea region of Ukraine, The Donetsk People's Republic (DNR), The Luhansk People's Republic (LNR), Kherson or Zaporizhzhia). If you are located in or are a national of one of the listed countries or regions, an export license may be required as a condition of your employment in this role. Please note that national origin and/or nationality do not affect eligibility for employment with Elastic. Please see here for our Privacy Statement.", "summaryDescription" : "Principal Software Engineer - Distributed Systems - Elasticsearch at Elastic", "postedDate" : "2026-06-14T20:42:17.926", "createdAt" : "2026-06-14T20:42:17.926", "lastUpdated" : "2026-06-16T01:04:03.979", "ingestTimestamp" : "2026-06-14T20:42:17.926", "mongoId" : "6a2c799474d8ee00a0941f11", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 10000000, "salaryAnnualMax" : 18000000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Executive", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2a660174d8ee00a062b6b0", "title" : "Software Development Engineer, Observability Insights", "company" : "Amazon Development Centre Ireland Limited", "industry" : "Software Development, no business category", "salary" : { "min" : 75000.0, "max" : 110000.0, "currency" : "EUR", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for a Mid-level Software Development Engineer in Dublin, Ireland, adjusted for company size and industry." }, "location" : "Dublin, IRL", "locations" : [ "Dublin, IRL" ], "timestamp" : "2026-06-15T07:50:39.362", "fingerprint" : "4f9034fea2dd30b0ae746fb0aa4ae383d7239f897a2d41b57c69db979b6a3487", "source" : "amazon", "language" : "en", "applyUrl" : "https://account.amazon.jobs/jobs/10443721/apply", "externalId" : "b5e857f7-a60f-421d-a55c-106f81495784", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Dublin", "country" : "Ireland", "continent" : "eu", "source" : "llm", "workMode" : "onsite", "geo" : "53.3493795,-6.2605593" } ], "locationText" : "Dublin, Ireland", "employmentType" : "FULL_TIME", "minimumEducation" : "Bachelor's", "technicalSkills" : "Distributed systems, Data pipelines, Real-time logs, Event data", "professionalSkills" : [ "System design", "Reliability", "Scaling" ], "hardSkillsList" : [ "Root cause analysis" ], "hardSkills" : [ { "name" : "Root cause analysis", "level" : "intermediate" } ], "majorSkills" : "Observability, Data processing", "majorSkillsList" : [ "Observability", "Data processing" ], "coreResponsibilities" : "Design distributed systems, Build distributed systems, Operate distributed systems, Process high-volume logs, Process real-time data, Deliver features, Improve product, Improve stakeholder services, Build data pipelines, Improve data pipelines, Handle terabytes per minute, Ship features, Surface correlations, Surface anomalies, Surface root-cause signals, Operate production services, Fix production issues, Collaborate across Org, Collaborate with partner functions, Plug insights into tooling, Drive automation, Reduce toil", "teamCollaboration" : "Partner functions; Internal customers; Senior engineers", "domainKnowledge" : "Amazon scale; Incident management; Change safety; Resilience tooling; Customer experience defects; Anomaly detection; Cross-signal insights", "domainList" : [ "amazon-scale", "incident-management", "change-safety", "resilience-tooling", "customer-experience-defects", "anomaly-detection", "cross-signal-insights" ], "domainSpecificKnowledge" : [ "Amazon scale", "Incident management", "Change safety", "Resilience tooling", "Customer experience defects", "Anomaly detection", "Cross-signal insights" ], "continuousLearning" : "Internal training; Learning opportunities; Innovation sprints; Hack days; Focused mentoring", "innovationCreativity" : "Innovation sprints; Hack days", "problemSolvingSkills" : "Root cause analysis", "outcomesObjectives" : "Pinpoint root causes in minutes; Contribute to availability; Contribute to resilience", "qualificationsBasic" : "Professional software development experience, Experience designing systems, Experience architecting systems, Programming with one language", "qualificationsPreferred" : "Bachelor's degree in computer science, Experience with full software development life cycle", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "The Observability Insights (OI) team owns own Tier-1 services used across Amazon's businesses to monitor, search, and visualise customer experience defects. Think: real-time correlations, anomaly detection, and cross-signal insights that help engineers pinpoint root causes in minutes, not hours. Our tools ingest and processes tens of TB/min of logs and other traffic. The insights we generate feed directly into incident management and prevention tooling across Amazon teams, including cross linking of insights with other signals. We are looking for a Software Development Engineer on our Observability Insights team. In this role you will design, build, and operate distributed systems that process high-volume, real-time logs and other event data at Amazon scale. You will work closely with senior engineers to deliver features and improvements to our product, and related stakeholder services — contributing directly to Amazon.com's availability and resilience! Key job responsibilities - Building and improving low-latency data pipelines that handle terabytes per minute - Shipping features that surface correlations, anomalies, and root-cause signals to internal engineering teams - Operating production Tier-1 services — with the context and training to actually fix things - Collaborating across our Org and partner functions (Incident Management, Change Safety, Platform teams, Internal customers) to plug our insights into broader resilience tooling - Driving automation that reduces toil and makes life better for engineers (including yourself!) You'll work closely with senior engineers who'll help you grow, and you'll have real ownership from day one. About the team - The team provides tools to help fast identification and mitigation of Amazon Customer impacting issues. We publish metrics and log based analytics that our users can use to proactively alarm on, and use to view trends in their telemetry - The team sits in Dublin but collaborates with internal Amazon teams worldwide - We are a high-trust, high-accountability culture - We are looking for folks to grow into future leaders in Amazon. We emphasise internal training and growth through learning opportunities, innovation sprints, hack days, and focused mentoring Basic Qualifications: - Experience (non-internship) in professional software development - Experience designing or architecting (design patterns, reliability and scaling) of new and existing systems - Experience programming with at least one software programming language Preferred Qualifications: - Bachelor's degree in computer science or equivalent - Experience with full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations Amazon is an equal opportunities employer. We believe passionately that employing a diverse workforce is central to our success. We make recruiting decisions based on your experience and skills. We value your passion to discover, invent, simplify and build. Protecting your privacy and the security of your data is a longstanding top priority for Amazon. Please consult our Privacy Notice ( https://www.amazon.jobs/en/privacy_page ) to know more about how we collect, use and transfer the personal data of our candidates. Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status. Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.", "summaryDescription" : "Software Development Engineer, Observability Insights at Amazon Development Centre Ireland Limited. Skills: Observability, Data processing. Design distributed systems. Build distributed systems", "postedDate" : "2026-06-14T01:39:39.907", "createdAt" : "2026-06-14T01:39:39.907", "lastUpdated" : "2026-06-15T07:50:39.362", "ingestTimestamp" : "2026-06-14T01:39:39.907", "mongoId" : "6a2a660174d8ee00a062b6b0", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "sourceUrl" : "https://account.amazon.jobs/jobs/10443721/apply", "salaryBand" : "75k-100k", "hasSalary" : false, "allSkills" : [ "Root cause analysis", "Observability", "Data processing", "System design", "Reliability", "Scaling", "Amazon scale", "Incident management", "Change safety", "Resilience tooling", "Customer experience defects", "Anomaly detection", "Cross-signal insights" ], "skillCount" : 13, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Mid", "dataQualityScore" : 0.8888889, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "69ce5e3b9bc74574cb677a4b", "title" : "Intern - Infrastructure Monitoring Analyst", "company" : "Mercedes-Benz Singapore Pte. Ltd.", "industry" : "Technology", "salary" : { "min" : 12000.0, "max" : 24000.0, "currency" : "SGD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for an entry-level internship in Singapore, adjusted for the technology industry and a large global company." }, "location" : "Singapore-Singapore-Singapore", "locations" : [ "Singapore-Singapore-Singapore", "1 Gateway Drive, 15-01 Westgate Tower, , Singapore" ], "timestamp" : "2026-06-15T09:35:33.617", "fingerprint" : "cff265bd7e11ca7933e973400d17b068151e03d2b1324a9a8dfbfab9f8c51c4b", "source" : "taleo", "language" : "en", "applyUrl" : "https://daimler.taleo.net/careersection/ex/jobdetail.ftl?job=886256", "externalId" : "886256", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Singapore", "state" : "Singapore", "country" : "Singapore", "continent" : "as", "source" : "llm", "workMode" : "onsite", "geo" : "1.2959845,103.7766186" } ], "locationText" : "Singapore, Singapore, Singapore", "employmentType" : "INTERNSHIP", "experienceMinYears" : 0, "experienceMaxYears" : 2, "experienceLevel" : "Entry", "technicalSkills" : "IT Infrastructure, Servers, Networks, Databases, Applications, Windows, Linux, SolarWinds, Splunk, Data analysis, Excel, Power BI, IT architecture", "professionalSkills" : [ "Information streamlining", "Data collection", "Configuration optimization", "Data analysis", "Trend identification", "Performance reporting", "Process optimization", "Vendor management" ], "hardSkillsList" : [ "Data interpretation", "Trend analysis", "Process documentation" ], "softSkillsList" : [ "Analytical thinking", "Problem-solving", "Team collaboration", "Process improvement" ], "hardSkills" : [ { "name" : "Data interpretation", "level" : "intermediate" }, { "name" : "Trend analysis", "level" : "intermediate" }, { "name" : "Process documentation", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Analytical thinking" }, { "name" : "Problem-solving" }, { "name" : "Team collaboration" }, { "name" : "Process improvement" } ], "majorSkills" : "Infrastructure monitoring, Data analysis, Process optimization", "majorSkillsList" : [ "Infrastructure monitoring", "Data analysis", "Process optimization" ], "coreResponsibilities" : "Collaborate with vendors, Optimize monitoring information flow, Review communication channels, Implement process improvements, Document streamlined processes, Assist monitoring data collection, Optimize tool configurations, Enhance data quality, Reduce data redundancy, Ensure data integrity, Analyze collected data, Interpret performance data, Identify potential issues, Assess streamlining impact, Create performance reports, Provide actionable insights, Identify reference architecture, Link architecture to monitoring", "teamCollaboration" : "Work with IT vendor; Work with internal teams; Collaborate with stakeholders", "domainKnowledge" : "IT infrastructure; Monitoring tools; IT architecture; Application stacks; Network segments; Database clusters", "domainList" : [ "it-infrastructure", "monitoring-tools", "it-architecture", "application-stacks", "network-segments", "database-clusters" ], "domainSpecificKnowledge" : [ "IT infrastructure", "Monitoring tools", "IT architecture", "Application stacks", "Network segments", "Database clusters" ], "toolProficiency" : [ "SolarWinds", "Splunk", "Excel", "Power BI" ], "communicationSkills" : "Verbal communication; Written communication; Report creation", "documentationSkills" : "Process documentation; Reference architecture documentation", "problemSolvingSkills" : "Problem-solving; Root cause analysis", "outcomesObjectives" : "Enhance monitoring efficiency; Enhance monitoring effectiveness; Ensure timely insights; Ensure accurate insights", "qualificationsBasic" : "Basic understanding IT infrastructure, Familiarity operating systems, Basic data analysis skills, Basic IT architecture concepts", "qualificationsPreferred" : "Basic knowledge IT monitoring tools, Foundational understanding IT architecture", "remoteFriendly" : false, "rawDescription" : "This internship project builds upon previous work, offering a hands-on experience in IT infrastructure monitoring, data analysis, and process optimization. The intern will continue to work closely with our IT vendor and internal teams, focusing on assisting with the ongoing collection of monitoring information and critically evaluating and streamlining the flow of this information from vendors. This role aims to enhance the efficiency and effectiveness of our monitoring processes, ensuring timely and accurate insights. An optional component of the project includes documenting the reference FMO architecture of infrastructure services and linking it to what is monitored. 1. Vendor Collaboration and Information Streamlining Objective: Collaborate with vendors to optimize the collection and flow of monitoring information, identifying opportunities for efficiency. Tasks: Review existing communication channels and data transfer methods with vendors for monitoring information. Propose and assist in implementing improvements for more efficient and automated data collection from vendor tools. Document streamlined processes and best practices for vendor information exchange. 2. Monitoring Data Collection and Configuration Optimization Objective: Assist in the ongoing collection of monitoring data and optimize tool configurations for improved data quality and accessibility. Tasks: Support the regular collection and organization of monitoring data from various tools and sources. Review and suggest improvements to monitoring tool configurations to enhance data relevance, reduce redundancy, and ensure data integrity. Ensure proper storage, accessibility, and version control of collected monitoring data and configurations. 3. Data Analysis and Trend Identification Objective: Analyze the data collected from the monitoring tools to interpret performance, identify potential issues, and assess the impact of streamlining efforts. Tasks: Collect and organize data from the monitoring tools, including data gathered through streamlined processes. Use analytical methods to interpret the data, identify trends, anomalies, and potential issues within the IT infrastructure. 4. Optional: Performance Reporting and Insights Objective: Create regular reports on IT infrastructure performance and provide insights based on the data analysis, highlighting improvements from streamlining. Tasks: Generate regular performance reports, incorporating data from optimized collection methods. Provide actionable insights and recommendations based on the analysis, including suggestions for further process improvements. 5. Optional: Reference Architecture and Monitoring Alignment Objective: Identify the reference architecture of various IT platforms and link them to the expected monitoring reports. Tasks: Work with internal teams and vendors to identify and document the reference architectures of key IT platforms (e.g., application stacks, network segments, database clusters). Analyze how the current monitoring tools and reports align with the critical components and dependencies within these architectures. Propose adjustments to monitoring configurations or reporting to ensure comprehensive coverage based on architectural insights. Technical Skills Basic Understanding of IT Infrastructure: Knowledge of servers, networks, databases, and applications. Familiarity with operating systems (Windows and Linux). Basic knowledge of common IT monitoring tools (e.g., SolarWinds, Splunk, etc.) is a plus. Basic skills in data analysis and interpretation. Familiarity with data visualization tools (e.g., Excel, Power BI, etc.). Foundational understanding of IT architecture concepts and components is a plus. Soft Skills Analytical Thinking: Strong analytical and problem-solving skills to interpret data, identify trends, pinpoint process inefficiencies, and understand architectural dependencies. Communication Skills: Good verbal and written communication skills for collaborating with vendors and internal teams, documenting findings, and creating clear, concise reports. Attention to Detail: Keen attention to detail for accurate data analysis, report generation, and process documentation. Team Collaboration: Ability to work effectively in a team environment and collaborate with various stakeholders. Process Improvement Mindset: A proactive approach to identifying and suggesting improvements for existing workflows and data collection methods. Mercedes-Benz Singapore Pte. Ltd.", "summaryDescription" : "Intern - Infrastructure Monitoring Analyst at Mercedes-Benz Singapore Pte. Ltd.. Skills: Infrastructure monitoring, Data analysis, Process optimization. Collaborate with vendors. Optimize monitoring information flow", "createdAt" : "2026-06-14T08:26:48.201", "lastUpdated" : "2026-06-15T09:35:33.617", "ingestTimestamp" : "2026-06-14T08:26:48.201", "mongoId" : "69ce5e3b9bc74574cb677a4b", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "<30k", "hasSalary" : false, "allSkills" : [ "Data interpretation", "Trend analysis", "Process documentation", "Analytical thinking", "Problem-solving", "Team collaboration", "Process improvement", "Infrastructure monitoring", "Data analysis", "Process optimization", "Information streamlining", "Data collection", "Configuration optimization", "Trend identification", "Performance reporting", "Vendor management", "IT infrastructure", "Monitoring tools", "IT architecture", "Application stacks", "Network segments", "Database clusters", "SolarWinds", "Splunk", "Excel", "Power BI" ], "skillCount" : 26, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Entry", "dataQualityScore" : 0.8888889, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 }, { "id" : "6a308b88f292fd229c0997b4", "title" : "Director, Data Governance & Observability", "company" : "Versant", "industry" : "Entertainment", "salary" : { "min" : 220000.0, "max" : 320000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for Director, Data Governance & Observability in New York, USA, adjusted for industry and company size." }, "location" : "New York, NEW YORK, United States", "locations" : [ "New York", "NEW YORK", "United States" ], "timestamp" : "2026-06-16T12:43:37.229", "fingerprint" : "083faf7ac4b5b5158195debef6ea81afc0e12580783497ca6bc50732544f64c9", "source" : "smartrecruiters", "language" : "en", "applyUrl" : "https://jobs.smartrecruiters.com/Versant3/744000131962953-director-data-governance-observability", "externalId" : "744000131962953", "industryFunction" : { }, "structuredLocations" : [ { "city" : "New York", "state" : "New York", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "40.7127281,-74.0060152" } ], "locationText" : "New York, New York, United States", "employmentType" : "FULL_TIME", "experienceMinYears" : 10, "experienceMaxYears" : 15, "experienceLevel" : "director", "remoteFriendly" : false, "rawDescription" : "VERSANT (Nasdaq: VSNT) is an industry-changing media and entertainment business and home to trusted brands that shape culture, inform audiences, and build lasting connections. It operates across four core markets: political news and opinion, business news and personal finance, golf, and sports and genre entertainment. These markets are served through a powerful portfolio of iconic and innovative brands, including CNBC, MS NOW, USA Network, Golf Channel, Oxygen, E!, SYFY, and Versant’s sports division USA Sports, along with complementary digital assets including Fandango, Rotten Tomatoes, GolfNow and GolfPass. Versant Media’s Data Platforms team is the central data store across the enterprise. We unify disparate systems into a secure, well-governed, real-time data environment that powers downstream products, analytics, and content delivery experiences. We are seeking a Director, Data Governance & Observability to establish and operationalize data governance as a first-class platform capability. This is a hands-on leadership role for someone who can both design and implement governance mechanisms in code, while also setting standards, prioritizing work, and partnering across the organization. This role will start as an individual contributor with leadership accountability , responsible for building the initial governance and observability foundations. Over time, the role is expected to grow into a people management position as scale and needs increase. The Director, Data Governance & Observability reports to the VP of Data Platforms and works in close partnership with Platform Development, Data Products & Solutions, and SRE. Responsibilities Data Governance & Contracts * Define and enforce data contracts across platform services and data products, including schemas, expectations, ownership, and change management * Establish standards for data lineage, metadata, and semantic consistency across the platform * Own definitions for data quality(freshness, completeness, correctness) and how those standards are validated * Partner with Platform Development to ensure governance requirements are embedded directly into pipelines, services, and APIs Observability & Reliability (Data-Level) * Define data-level SLIs and SLOs in partnership with the SRE organization * Ensure contract violations, quality failures, and freshness issues are observable and actionable * Build and maintain platform-facing health and operational dashboards related to data services * Contribute to light executive-level reporting on platform health and data reliability (not business analytics) Hands-On Platform Development * Write production code to implement governance and observability mechanisms (e.g., schema validation, contract enforcement, lineage capture) * Contribute to shared platform libraries, services, and tooling that make compliant behavior the default * Review designs and code to ensure governance considerations are addressed early Cross-Functional Leadership * Partner closely with: * Director, Platform Development on schemas, contracts, and platform enforcement patterns * Director, Data Products & Solutions on base dashboards, self-service enablement, and consumer-facing trust signals * SRE on alerting strategy, incident classification, and reliability standards * Help triage and prioritize governance-related intake and tradeoffs * Clearly communicate standards and expectations to engineering and non-engineering stakeholders Team Growth (Future) * Hire and mentor data platform engineers focused on governance and quality as needs scale * Gradually transition toward more people leadership and strategic ownership over time ## Qualifications * 10+ years Strong hands-on experience building production data or platform systems * Deep understanding of data governance concepts, including contracts, lineage, metadata, and quality * Experience defining and enforcing standards through code and automation, not just documentation * Solid software engineering foundation, including: * API and schema design * Modular or service-oriented architectures * Automated testing and CI/CD practices * Familiarity with observability concepts and working with SRE teams * Comfortable operating with high ownership in a lean, fast-moving environment * Strong collaborator who can work across platform, product, analytics, and operations teams Nice to Have * Experience working in large-scale enterprise or media environments * Familiarity with lakehouse architectures and ELT pipelines * Exposure to analytics or BI tooling (e.g., Tableau, Power BI) from a platform or enablement perspective * Experience modernizing or governing legacy data systems in cloud-native environments ## Additional Information As part of our selection process, external candidates may be required to attend an in-person interview with a VERSANT Media employee at one of our locations prior to a hiring decision. VERSANT Media's policy is to provide equal employment opportunities to all applicants and employees without regard to race, color, religion, creed, gender, gender identity or expression, age, national origin or ancestry, citizenship, disability, sexual orientation, marital status, pregnancy, veteran status, membership in the uniformed services, genetic information, or any other basis protected by applicable law. If you are a qualified individual with a disability or a disabled veteran and require support throughout the application and/or recruitment process as a result of your disability, you have the right to request a reasonable accommodation. You can submit your request to [candidateaccessibility@versantmedia.com](mailto:candidateaccessibility@versantmedia.com). VERSANT Media is committed to fair and equitable compensation practices. We include a good faith pay range for each position to comply with applicable state and local pay transparency laws and to promote equity across our organization. Actual compensation will be based on factors such as the candidate's skills, qualifications, experience, and location and may include additional forms of compensation and benefits such as health insurance, retirement plans, paid time off, etc. VERSANT Media is not accepting unsolicited assistance from search firms for this employment opportunity. All resumes submitted by search firms to any employee at VERSANT via-email, the Internet, or in any form and/or method without a valid written Statement of Work in place for this position from VERSANT's Talent Acquisition team will be deemed the sole property of VERSANT. No fee will be paid in the event the candidate is hired by VERSANT as a result of the referral or through other means.", "summaryDescription" : "Director, Data Governance & Observability at Versant", "postedDate" : "2026-06-12T18:37:58.000", "createdAt" : "2026-06-16T03:31:54.024", "lastUpdated" : "2026-06-16T12:43:37.229", "ingestTimestamp" : "2026-06-16T03:31:54.024", "mongoId" : "6a308b88f292fd229c0997b4", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 220000, "salaryAnnualMax" : 320000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ ], "skillCount" : 0, "jobCategory" : "engineering", "jobSubcategory" : "data", "seniorityLevel" : "Director", "dataQualityScore" : 0.8888889, "daysOld" : 3, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Media", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2c7c0774d8ee00a094c037", "title" : "Distributed Systems Engineer, Analytical Database Platform", "company" : "Cloudflare", "industry" : "Technology", "salary" : { "min" : 165000.0, "max" : 235000.0, "currency" : "USD", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market baseline for a Mid-level, Senior Distributed Systems Engineer in Austin, United States, adjusted for the Technology industry and a large company size." }, "location" : "Austin, TX, United States", "locations" : [ "Austin", "TX", "United States" ], "timestamp" : "2026-06-15T11:22:56.393", "fingerprint" : "826f36ab80a20a86769f35dd9ce1c345aa7dd650d93e84042ae99e3dd0c6ef67", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://boards.greenhouse.io/cloudflare/jobs/7462799?gh_jid=7462799", "externalId" : "7462799", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Austin", "state" : "Texas", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "onsite", "geo" : "30.2711286,-97.7436995" } ], "locationText" : "Austin, Texas, United States", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Golang, Python, C++, SQL, Databases, Distributed systems, Docker, Kubernetes", "professionalSkills" : [ "Software development", "Database design", "Performance tuning", "Data ingestion" ], "hardSkillsList" : [ "Database internals", "Algorithms", "Data structures", "Concurrency" ], "hardSkills" : [ { "name" : "Database internals", "level" : "intermediate" }, { "name" : "Algorithms", "level" : "intermediate" }, { "name" : "Data structures", "level" : "intermediate" }, { "name" : "Concurrency", "level" : "intermediate" } ], "majorSkills" : "Distributed systems, Analytical database, ClickHouse", "majorSkillsList" : [ "Distributed systems", "Analytical database", "ClickHouse" ], "coreResponsibilities" : "Develop platform components, Implement platform components, Add database clusters, Monitor cluster performance, Maintain cluster reliability, Troubleshoot database issues, Identify bottlenecks, Remove bottlenecks, Optimize query performance, Streamline data ingestion, Collaborate with community, Add new features, Contribute to codebase, Understand data needs, Build data solutions, Participate in development, Research new technologies, Evaluate new technologies", "teamCollaboration" : "Collaborate in team; Communicate with teams", "domainKnowledge" : "Analytical database; Distributed systems; Database internals; Cloudflare Analytics", "domainList" : [ "analytical-database", "distributed-systems", "database-internals", "cloudflare-analytics" ], "domainSpecificKnowledge" : [ "Analytical database", "Distributed systems", "Database internals", "Cloudflare Analytics" ], "toolProficiency" : [ "ClickHouse", "SALT", "Terraform", "Docker", "Kubernetes" ], "communicationSkills" : "Effective communication", "problemSolvingSkills" : "Analytical; Problem-solving; Proactive issue identification", "qualificationsBasic" : "3+ years software development, Distributed systems experience, Databases experience, Golang programming skills, Python programming skills, C++ programming skills, SQL knowledge, Database internals knowledge, Computer science foundation, Algorithms knowledge, Data structures knowledge, Concurrency knowledge, Team environment work, Effective communication skills, Analytical skills, Problem-solving skills, Independent work ability, Proactive issue identification", "qualificationsPreferred" : "ClickHouse experience, SALT experience, Terraform experience, Linux container technologies experience, Docker experience, Kubernetes experience", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "About Us At Cloudflare, we are on a mission to help build a better Internet. Today the company runs one of the world’s largest networks that powers millions of websites and other Internet properties for customers ranging from individual bloggers to SMBs to Fortune 500 companies. Cloudflare protects and accelerates any Internet application online without adding hardware, installing software, or changing a line of code. Internet properties powered by Cloudflare all have web traffic routed through its intelligent global network, which gets smarter with every request. As a result, they see significant improvement in performance and a decrease in spam and other attacks. Cloudflare was named to Entrepreneur Magazine’s Top Company Cultures list and ranked among the World’s Most Innovative Companies by Fast Company. At Cloudflare, we’re not looking for people who wait for a polished roadmap; we’re looking for the builders who see the cracks in the Internet that everyone else has simply learned to live with. We value candidates who have the instinct to spot a \"normalized\" problem and the AI-native curiosity to create a solution using the latest tools. Our culture is built on iteration, leveraging AI to ship faster today to make it better tomorrow, while ensuring that every improvement, no matter how small, is shared across the team to lift everyone up. If you’re the type of person who values curiosity over bureaucracy, and that AI is a partner in solving tough problems to keep the Internet moving forward, you’ll fit right in. Locations Available: Austin (US) About Role We are looking for an experienced and highly motivated engineer to join our team and contribute to our analytical database platform. The platform is a critical component of Cloudflare Analytics which provides real-time visibility into the health and performance of Cloudflare customers' online properties. The team builds and maintains a high-performance, scalable database platform powered by ClickHouse, optimized for analytical workloads. We help our customers, both internal and external, to gain a deeper understanding of their online properties, identify trends and patterns, and make informed decisions about how to optimize their web performance, security, and other key metrics. Our mission is to empower customers to leverage their data to drive better outcomes for their business. As a Distributed systems engineer - Analytical Database Platform, you will: Develop and implement new platform components for the Cloudflare Analytical Database Platform to improve functionality and performance. Add more database clusters to accommodate the growing volume of data generated by Cloudflare products and services. Monitor and maintain the performance and reliability of existing database platform clusters, and identify and troubleshoot any issues that may arise. Work to identify and remove bottlenecks within the analytics database platform, including optimizing query performance and streamlining data ingestion processes. Collaborate with the ClickHouse open-source community to add new features and functionality to the database, as well as contribute to the development of the upstream codebase. Collaborate with other teams across Cloudflare to understand their data needs and build solutions that empower them to make data-driven decisions. Participate in the development of the next generation of the database platform engine, including researching and evaluating new technologies and approaches that can improve the database's performance and scalability. Key qualifications: 3+ years of experience working in software development covering distributed systems, and databases. Strong programming skills (Golang, python, C++ are preferable), as well as a deep understanding of software development best practices and principles. Strong knowledge of SQL and database internals, including experience with database design, optimization, and performance tuning. A solid foundation in computer science, including algorithms, data structures, distributed systems, and concurrency. Ability to work collaboratively in a team environment, as well as communicate effectively with other teams across Cloudflare. Strong analytical and problem-solving skills, as well as the ability to work independently and proactively identify and solve issues. Experience with ClickHouse is a plus. Experience with SALT or Terraform is a plus. Experience with Linux container technologies, such as Docker and Kubernetes, is a plus. If you're passionate about building scalable and performant databases using cutting-edge technologies, and want to work with a world-class team of engineers, then we want to hear from you! Join us in our mission to help build a better internet for everyone! This role may require flexibility to be on-call outside of standard working hours to address technical issues as needed. What Makes Cloudflare Special? We’re not just a highly ambitious, large-scale technology company. We’re a highly ambitious, large-scale technology company with a soul. Fundamental to our mission to help build a better Internet is protecting the free and open Internet. Project Galileo: Since 2014, we've equipped more than 2,400 journalism and civil society organizations in 111 countries with powerful tools to defend themselves against attacks that would otherwise censor their work, technology already used by Cloudflare’s enterprise customers--at no cost. Athenian Project: In 2017, we created the Athenian Project to ensure that state and local governments have the highest level of protection and reliability for free, so that their constituents have access to election information and voter registration. Since the project, we've provided services to more than 425 local government election websites in 33 states. 1.1.1.1: We released 1.1.1.1 to help fix the foundation of the Internet by building a faster, more secure and privacy-centric public DNS resolver. This is available publicly for everyone to use - it is the first consumer-focused service Cloudflare has ever released. Here’s the deal - we don’t store client IP addresses never, ever. We will continue to abide by our privacy commitment and ensure that no user data is sold to advertisers or used to target consumers. Sound like something you’d like to be a part of? We’d love to hear from you! Please note that applicants who progress to the offer stage of the interview process may be asked to attend an in-person interview within one of the Cloudflare Offices or Cloudflare Hubs. More details about this will be available at that stage of the interview process. This position may require access to information protected under U. S. export control laws, including the U. S. Export Administration Regulations. Please note that any offer of employment may be conditioned on your authorization to receive software or technology controlled under these U. S. export laws without sponsorship for an export license. Cloudflare is proud to be an equal opportunity employer. We are committed to providing equal employment opportunity for all people and place great value in both diversity and inclusiveness. All qualified applicants will be considered for employment without regard to their, or any other person's, perceived or actual race, color, religion, sex, gender, gender identity, gender expression, sexual orientation, national origin, ancestry, citizenship, age, physical or mental disability, medical condition, family care status, or any other basis protected by law. We are an AA/Veterans/Disabled Employer. Cloudflare provides reasonable accommodations to qualified individuals with disabilities. Please tell us if you require a reasonable accommodation to apply for a job. Examples of reasonable accommodations include, but are not limited to, changing the application process, providing documents in an alternate format, using a sign language interpreter, or using specialized equipment. If you require a reasonable accommodation to apply for a job, please contact us via e-mail at hr@cloudflare.com or via mail at 101 Townsend St. San Francisco, CA 94107.", "summaryDescription" : "Distributed Systems Engineer, Analytical Database Platform at Cloudflare. Skills: Distributed systems, Analytical database, ClickHouse. Develop platform components. Implement platform components", "postedDate" : "2026-06-14T09:12:53.966", "createdAt" : "2026-06-14T09:12:53.966", "lastUpdated" : "2026-06-15T11:22:56.393", "ingestTimestamp" : "2026-06-14T09:12:53.966", "mongoId" : "6a2c7c0774d8ee00a094c037", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 165000, "salaryAnnualMax" : 235000, "salaryBand" : "150k-200k", "hasSalary" : true, "allSkills" : [ "Database internals", "Algorithms", "Data structures", "Concurrency", "Distributed systems", "Analytical database", "ClickHouse", "Software development", "Database design", "Performance tuning", "Data ingestion", "Cloudflare Analytics", "SALT", "Terraform", "Docker", "Kubernetes" ], "skillCount" : 16, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Mid", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2c799674d8ee00a0941f6c", "title" : "Senior Java Engineer - Distributed Systems - Elasticsearch", "company" : "Elastic", "industry" : "Technology", "salary" : { "min" : 85600.0, "max" : 135500.0, "currency" : "EUR", "frequency" : "yearly", "is_estimated" : false }, "location" : "Distributed, Global", "locations" : [ "Distributed", "Global" ], "timestamp" : "2026-06-15T10:20:45.279", "fingerprint" : "156807c2fbbc30bf8a17389c3b9b5a1dbc3753ac189b0357ff361719d56f6ce4", "source" : "greenhouse", "language" : "en", "applyUrl" : "https://jobs.elastic.co/jobs?gh_jid=8001186&gh_jid=8001186", "externalId" : "8001186", "industryFunction" : { }, "structuredLocations" : [ { "workMode" : "remote" } ], "locationText" : "", "employmentType" : "FULL_TIME", "experienceMinYears" : 5, "experienceMaxYears" : 10, "experienceLevel" : "Senior", "technicalSkills" : "Java, Data structures, Concurrency, Elasticsearch", "professionalSkills" : [ "Technical design", "System design" ], "hardSkillsList" : [ "Distributed systems", "Consensus algorithms", "Indexing", "Cluster coordination", "Performance tuning", "Concurrency tuning" ], "hardSkills" : [ { "name" : "Distributed systems", "level" : "intermediate" }, { "name" : "Consensus algorithms", "level" : "intermediate" }, { "name" : "Indexing", "level" : "intermediate" }, { "name" : "Cluster coordination", "level" : "intermediate" }, { "name" : "Performance tuning", "level" : "intermediate" }, { "name" : "Concurrency tuning", "level" : "intermediate" } ], "majorSkills" : "Distributed systems, Java, Elasticsearch", "majorSkillsList" : [ "Distributed systems", "Java", "Elasticsearch" ], "coreResponsibilities" : "Improve Elasticsearch components, Support concurrent indexing, Support consistent indexing, Maintain cluster coordination system, Keep performance high, Maintain safety properties, Maintain liveness properties, Push limits on shards, Push limits on nodes, Push limits on petabytes, Investigate performance issues, Investigate concurrency issues, Propose solutions, Support support engineers, Work with others to develop components", "teamCollaboration" : "Working with others", "domainKnowledge" : "Distributed systems; Search AI; Elasticsearch Platform; Search; Security; Observability; Data stores; Indexing; Shards; Nodes; Petabytes; Cluster coordination; Data allocation; Data replication; Consensus algorithms", "domainList" : [ "distributed-systems", "search-ai", "elasticsearch-platform", "search", "security", "observability", "data-stores", "indexing", "shards", "nodes", "petabytes", "cluster-coordination", "data-allocation", "data-replication", "consensus-algorithms" ], "domainSpecificKnowledge" : [ "Distributed systems", "Search AI", "Elasticsearch Platform", "Search", "Security", "Observability", "Data stores", "Indexing", "Shards", "Nodes", "Petabytes", "Cluster coordination", "Data allocation", "Data replication", "Consensus algorithms" ], "problemSolvingSkills" : "Problem solving", "qualificationsBasic" : "Background in distributed systems, Background in consensus algorithms, Skills in core Java, Conversant in standard library, Conversant in concurrency constructs, Conversant in newer language features, Deep technical proficiency in algorithms, Ability to understand complex systems, Ability to work on complex systems, Ability to understand highly distributed systems, Ability to work on highly distributed systems, Ability to build features with broad impact, Ability to debug features with broad impact, Ability to own projects from beginning to end, Ability to develop needed components", "qualificationsPreferred" : "Data stores knowledge, Search knowledge, Analytics knowledge, Lucene knowledge, JDK knowledge, Asynchronous event-driven network frameworks knowledge, Netty knowledge", "remoteFriendly" : true, "workSiteFlexibility" : "Remote", "rawDescription" : "Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI. What Is The Role: We are on the lookout for a Senior Software Engineer to join our Elasticsearch - Distributed Systems team and focus on how Elasticsearch provides scale, performance, and resilience. This team owns how nodes in an Elasticsearch cluster communicate, and how data are indexed, allocated, and replicated across nodes. What You Will Be Doing: Improving Elasticsearch’s components that support concurrent and consistent indexing across multiple machines. Maintaining our cluster coordination system to keep performance high even though nodes come and go from the cluster and data moves around, while maintaining the safety and liveness properties of the system as a whole. Pushing the limits on the number of shards, nodes, and petabytes that Elasticsearch can handle today Looking into all kinds of issues, including performance or concurrency issues, and proposing solutions. Supporting our support engineers with the harder problems. What You Bring: A strong background in distributed systems and consensus algorithms. You have strong skills in core Java and are conversant in the standard library of data structures and concurrency constructs, as well as newer language features. You have a deep technical proficiency in algorithms. You have shown your ability to understand and work on complex, highly distributed systems. You demonstrate the ability to build and debug features with a broad impact, running on multiple machines. You are able to own projects from beginning to end. This covers both technical design and working with others to develop needed components. Bonus Points: Data stores Search, analytics, Lucene Strong knowledge of the JDK Asynchronous event-driven network frameworks such as Netty Compensation for this role is in the form of base salary. This role does not have a variable compensation component. At Elastic, our compensation philosophy aims to provide fair, competitive and transparent remuneration. Salary ranges are established based on a combination of external market benchmarks, internal pay equity considerations, and the responsibilities and complexity associated with each role. This approach helps ensure consistency across comparable roles while remaining competitive within the relevant labour markets. The final compensation offered within the applicable range will be determined based on several objective factors, including relevant professional experience, level of skills and expertise, alignment with the role requirements, and the overall scope and complexity of the position. The typical starting salary range for this role is: €85.600—€135.500 EUR Additional Information - We Take Care of Our People As a distributed company, diversity drives our identity. Whether you’re looking to launch a new career or grow an existing one, Elastic is the type of company where you can balance great work with great life. Your age is only a number. It doesn’t matter if you’re just out of college or your children are; we need you for what you can do. We strive to have parity of benefits across regions and while regulations differ from place to place, we believe taking care of our people is the right thing to do. Competitive pay based on the work you do here and not your previous salary Health coverage for you and your family in many locations Ability to craft your calendar with flexible locations and schedules for many roles Generous number of vacation days each year Increase your impact - We match up to $2000 (or local currency equivalent) for financial donations and service Up to 40 hours each year to use toward volunteer projects you love Embracing parenthood with minimum of 16 weeks of parental leave Different people approach problems differently. We need that. Elastic is an equal opportunity employer and is committed to creating an inclusive culture that celebrates different perspectives, experiences, and backgrounds. Qualified applicants will receive consideration for employment without regard to race, ethnicity, color, religion, sex, pregnancy, sexual orientation, gender perception or identity, national origin, age, marital status, protected veteran status, disability status, or any other basis protected by federal, state or local law, ordinance or regulation. We welcome individuals with disabilities and strive to create an accessible and inclusive experience for all individuals. To request an accommodation during the application or the recruiting process, please email candidate_accessibility@elastic.co. We will reply to your request within 24 business hours of submission. Applicants have rights under Federal Employment Laws, view posters linked below: Family and Medical Leave Act (FMLA) Poster; Pay Transparency Nondiscrimination Provision Poster; Employee Polygraph Protection Act (EPPA) Poster and Know Your Rights (Poster) Elasticsearch develops and distributes technology and information that is subject to U. S. and other countries’ export controls and licensing requirements for individuals who are located in or are nationals of the following sanctioned countries and regions: Belarus, Cuba, Iran, North Korea, Syria, or Russia, including the Ukrainian territories annexed by Russia (The Crimea region of Ukraine, The Donetsk People's Republic (DNR), The Luhansk People's Republic (LNR), Kherson or Zaporizhzhia). If you are located in or are a national of one of the listed countries or regions, an export license may be required as a condition of your employment in this role. Please note that national origin and/or nationality do not affect eligibility for employment with Elastic. Please see here for our Privacy Statement.", "summaryDescription" : "Senior Java Engineer - Distributed Systems - Elasticsearch at Elastic. Skills: Distributed systems, Java, Elasticsearch. Improve Elasticsearch components. Support concurrent indexing", "postedDate" : "2026-06-14T09:08:04.654", "createdAt" : "2026-06-14T09:08:04.654", "lastUpdated" : "2026-06-15T10:20:45.279", "ingestTimestamp" : "2026-06-14T09:08:04.654", "mongoId" : "6a2c799674d8ee00a0941f6c", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "75k-100k", "hasSalary" : false, "allSkills" : [ "Distributed systems", "Consensus algorithms", "Indexing", "Cluster coordination", "Performance tuning", "Concurrency tuning", "Java", "Elasticsearch", "Technical design", "System design", "Search AI", "Elasticsearch Platform", "Search", "Security", "Observability", "Data stores", "Shards", "Nodes", "Petabytes", "Data allocation", "Data replication" ], "skillCount" : 21, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 1, "hasLocation" : true, "hasGeo" : false, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a2ce82974d8ee00a0a69c91", "title" : "Staff Product Manager, Agent Observability", "company" : "LiveKit", "industry" : "R&D", "salary" : { "min" : 225000.0, "max" : 265000.0, "currency" : "USD", "frequency" : "Yearly" }, "location" : "Hybrid, San Francisco", "locations" : [ "Hybrid, San Francisco" ], "timestamp" : "2026-06-15T07:17:15.537", "fingerprint" : "c4374edf6e27367f4ad57c59d6fab40bcda6914bad95dacb33fba8c00725f870", "source" : "ashby", "language" : "en", "applyUrl" : "https://jobs.ashbyhq.com/livekit/dc2e64b8-15fd-4d88-b2dd-c3106f76df4d/application", "externalId" : "dc2e64b8-15fd-4d88-b2dd-c3106f76df4d", "industryFunction" : { }, "structuredLocations" : [ { "city" : "San Francisco", "state" : "California", "country" : "United States", "continent" : "na", "source" : "llm", "workMode" : "hybrid", "geo" : "37.7879363,-122.4075201" } ], "locationText" : "San Francisco, California, United States", "employmentType" : "FULL_TIME", "experienceLevel" : "Manager", "technicalSkills" : "AI, LLM", "professionalSkills" : [ "Product strategy", "Roadmap development", "User stories", "Cross-functional collaboration", "Systems reasoning", "Design judgment", "Product sense", "Influence", "Prioritization" ], "hardSkillsList" : [ "Agent quality measurement", "Latency measurement", "Cost measurement", "Conversation quality measurement", "Agent behavior measurement" ], "softSkillsList" : [ "Obsessed with customers", "Go-to person", "Work hard", "Focused on polish", "Focused on detail", "Focused on quality" ], "hardSkills" : [ { "name" : "Agent quality measurement", "level" : "intermediate" }, { "name" : "Latency measurement", "level" : "intermediate" }, { "name" : "Cost measurement", "level" : "intermediate" }, { "name" : "Conversation quality measurement", "level" : "intermediate" }, { "name" : "Agent behavior measurement", "level" : "intermediate" } ], "softSkills" : [ { "name" : "Obsessed with customers" }, { "name" : "Go-to person" }, { "name" : "Work hard" }, { "name" : "Focused on polish" }, { "name" : "Focused on detail" }, { "name" : "Focused on quality" } ], "majorSkills" : "Agent Observability, Product Management, AI Agents, Voice AI", "majorSkillsList" : [ "Agent Observability", "Product Management", "AI Agents", "Voice AI" ], "coreResponsibilities" : "Own observability roadmap, Set clear vision, Set sequenced plan, Decide what gets built, Ship products people rely on, Turn complex problem into experiences, Raise bar on quality, Make agent quality measurable, Build evals for teams, Build metrics for teams, Design for technical users, Design for non-technical operators, Get deep with customers, Get deep with data, Understand how teams run agents, Understand how teams debug agents, Grow observability into business, Drive adoption, Drive revenue", "teamCollaboration" : "Partner with engineering; Influence engineering teams", "projectManagementSkills" : [ "Roadmap planning" ], "domainKnowledge" : "Agentic era computing; AI agents; Voice AI observability; Real-time communication; Telephony", "domainList" : [ "agentic-era-computing", "ai-agents", "voice-ai-observability", "real-time-communication", "telephony" ], "domainSpecificKnowledge" : [ "Agentic era computing", "AI agents", "Voice AI observability", "Real-time communication", "Telephony" ], "communicationSkills" : "Write clearly; Present well; Board-level strategy; Technical discussion", "problemSolvingSkills" : "Tackle tough problems; Reason about systems; Make tradeoffs; Prioritize ruthlessly", "outcomesObjectives" : "Observability revenue reflects value", "qualificationsBasic" : "8+ years in product management, Senior or staff level experience, Owned a developer-facing product, Owned a data-heavy product, Technical depth, Multi-persona product sense, Cross-functional influence, Communication as a superpower, Comfort with ambiguity", "qualificationsPreferred" : "Built an observability product, Built a monitoring product, Built an analytics product, Built tool for evaluating AI quality, Built tool for improving AI quality, Familiarity with evals for AI, Familiarity with tracing for AI, Familiarity with quality measurement for AI, Familiarity with debugging software, Familiarity with monitoring software, Familiarity with logs, Familiarity with traces, Familiarity with metrics, Familiarity with dashboards, Background at developer tools company, Background at infrastructure company, Familiarity with voice AI, Familiarity with real-time communication, Familiarity with telephony", "remoteFriendly" : true, "workSiteFlexibility" : "Hybrid", "rawDescription" : "ABOUT LIVEKIT LiveKit is building the infrastructure layer for the agentic era of computing. Our platform gives developers everything they need to build, test, deploy, scale, and observe AI agents in production. Founded in 2021, LiveKit powers voice and agentic AI applications for OpenAI, Salesforce, Spotify, Meta, and tens of thousands of other developers, collectively facilitating billions of calls each year. ABOUT THIS ROLE We're looking for a Product Manager to own LiveKit's Agent Observability product: how teams understand, debug, and trust what their voice agents do in production. Our PM team is small and high-leverage, with each PM coming in to establish the foundations in a new area of the business. Observability is one of the most important new products at LiveKit. It's central to our strategy, a surface of huge value to customers, and a category still in its infancy. You'd own it as the sole PM. You'll set the vision and roadmap for the whole observability suite, from traces and recordings to dashboards, evals, and quality metrics, and partner closely with the engineering team that builds it. The product has to serve two very different users at once: the engineer debugging why a call went wrong, and the non-technical operator reviewing quality, cost, and agent behavior. That makes it as hard at the UX layer as it is under the hood. The category for voice AI observability is being defined right now, and you'll be shaping a product used by some of the largest companies deploying voice agents at scale. YOU'LL THRIVE AT LIVEKIT IF YOU: - are obsessed with making the best product for our customers - are known as the go-to person for tackling tough problems - work hard and can build and ship fast - are focused on polish, detail, and quality - are a fast learner, frequently picking up new tips, tricks, and skills The best way to impress us is by trying LiveKit’s product, understanding the space, and bringing smart thoughts and opinions to the table. WHAT YOU'LL DO - Own the observability roadmap. Set a clear vision and a sequenced plan for the suite, and decide what gets built and when, in partnership with engineering. - Ship products people rely on. Turn a complex, data-dense problem into experiences customers use every day, and keep raising the bar on quality. - Make agent quality measurable. Build the evals and metrics teams need to know whether their agents are actually good and getting better, from latency and cost to conversation quality and behavior. - Design for two audiences at once. Make the product work for deeply technical users and non-technical operators without compromising either. - Get deep with customers and data. Understand how teams actually run and debug agents in production, and let that shape priorities. - Grow it into a business. Drive adoption and revenue so our observability revenue reflects the real value it delivers to customers. WHO YOU ARE - 8+ years in product management, at a senior or staff level, ideally having owned a developer-facing or data-heavy product. - Technical depth. You can reason about how a complex system works under the hood and earn the trust of strong engineers. You don't need to write code, but you need to understand systems well enough to make good tradeoffs. - Multi-persona product sense. You've built for both deeply technical users and non-technical ones in the same product, and have the design judgment to make dense, data-rich interfaces genuinely useful. - Cross-functional influence. LiveKit's engineering teams operate with high autonomy. You influence through clarity, trust, and good judgment, not process or hierarchy. - Communication as a superpower. You write clearly, present well, and can move between a board-level strategy conversation and a detailed technical discussion with an engineering lead. - Comfort with ambiguity. We're a small product team at a fast-growing company. You'll figure out what matters, prioritize ruthlessly, and move quickly without perfect information. NICE TO HAVE - Built an observability, monitoring, or analytics product, or a tool for evaluating and improving AI/LLM quality - Familiarity with evals, tracing, or quality measurement for AI/LLM or agent systems - Familiarity with how teams debug and monitor software in production (logs, traces, metrics, dashboards) - Background at a developer tools or infrastructure company - Familiarity with voice AI, real-time communication, or telephony - Experience with usage-based pricing models OUR COMMITMENT TO YOU - An opportunity to build something truly impactful to the world - Contribute to open source alongside world-class engineers - Competitive salary and equity package - Health, dental, and vision benefits - Flexible vacation policy LiveKit is an equal opportunity employer and does not discriminate on the basis of any characteristic protected by applicable law. If you require a reasonable accommodation during the application or interview process, please contact recruiting@livekit.io.", "summaryDescription" : "Staff Product Manager, Agent Observability at LiveKit. Skills: Agent Observability, Product Management, AI Agents, Voice AI. Own observability roadmap. Set clear vision", "createdAt" : "2026-06-13T22:13:12.769", "lastUpdated" : "2026-06-15T07:17:15.537", "ingestTimestamp" : "2026-06-13T22:13:12.769", "mongoId" : "6a2ce82974d8ee00a0a69c91", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryAnnualMin" : 225000, "salaryAnnualMax" : 265000, "salaryBand" : "200k+", "hasSalary" : true, "allSkills" : [ "Agent quality measurement", "Latency measurement", "Cost measurement", "Conversation quality measurement", "Agent behavior measurement", "Obsessed with customers", "Go-to person", "Work hard", "Focused on polish", "Focused on detail", "Focused on quality", "Agent Observability", "Product Management", "AI Agents", "Voice AI", "Product strategy", "Roadmap development", "User stories", "Cross-functional collaboration", "Systems reasoning", "Design judgment", "Product sense", "Influence", "Prioritization", "Roadmap planning", "Agentic era computing", "AI agents", "Voice AI observability", "Real-time communication", "Telephony" ], "skillCount" : 30, "jobCategory" : "product", "jobSubcategory" : "product_management", "seniorityLevel" : "Executive", "dataQualityScore" : 0.8888889, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.98 }, { "id" : "6a306b2ff292fd229cfcf981", "title" : "Ingénieur Observability – Elastic Stack (H/F)", "company" : "SQLI", "industry" : "Information Technology And Services", "salary" : { "min" : 135000.0, "max" : 175000.0, "currency" : "CHF", "frequency" : "yearly", "is_estimated" : true, "estimation_basis" : "Market data for a Senior Observability Engineer in Geneva, Switzerland, adjusted for the technology industry and a large company size." }, "location" : "Genève, GE, CH", "locations" : [ "Genève", "GE", "CH" ], "timestamp" : "2026-06-16T07:48:09.200", "fingerprint" : "80ce980f6c95848f1ee63de5ce8b2f0e57a0afc7c4797d20e73720ab8a7564d5", "source" : "smartrecruiters", "language" : "fr", "applyUrl" : "https://jobs.smartrecruiters.com/SQLI1/744000132188496-ingenieur-observability-elastic-stack-h-f-", "externalId" : "744000132188496", "industryFunction" : { }, "structuredLocations" : [ { "city" : "Genève", "state" : "Geneva", "country" : "Switzerland", "continent" : "eu", "source" : "llm", "workMode" : "onsite", "geo" : "46.2017559,6.1466014" } ], "locationText" : "Genève, Geneva, Switzerland", "employmentType" : "FULL_TIME", "experienceMinYears" : 0, "experienceMaxYears" : 2, "experienceLevel" : "entry", "technicalSkills" : "Elasticsearch, Kibana, Logstash, Beats, APM, Kubernetes", "professionalSkills" : [ "Architecture", "Gouvernance technique" ], "hardSkillsList" : [ "Observability", "Logs", "Metrics", "Traces" ], "hardSkills" : [ { "name" : "Observability", "level" : "intermediate" }, { "name" : "Logs", "level" : "intermediate" }, { "name" : "Metrics", "level" : "intermediate" }, { "name" : "Traces", "level" : "intermediate" } ], "majorSkills" : "Elastic Stack, Observability", "majorSkillsList" : [ "Elastic Stack", "Observability" ], "coreResponsibilities" : "Concevoir et mettre en œuvre des solutions d’observabilité, Définir les standards, l’architecture et les bonnes pratiques, Participer à la gouvernance technique, Structurer le programme, Mettre en place dashboards, Mettre en place alerting, Mettre en place visualisations, Accompagner les équipes dans l’adoption des solutions, Documenter les processus, Assurer le partage de connaissances", "teamCollaboration" : "Environnements hybrides; Environnements complexes et transverses; Équipes pluridisciplinaires", "domainKnowledge" : "Environnement IT critique; VM; Containers", "domainList" : [ "environnement-it-critique", "vm", "containers" ], "domainSpecificKnowledge" : [ "Environnement IT critique", "VM", "Containers" ], "toolProficiency" : [ "Elastic Stack" ], "communicationSkills" : "Vulgarisation", "documentationSkills" : "Documenter les processus", "continuousLearning" : "Formation continue", "innovationCreativity" : "Innovation", "outcomesObjectives" : "Construire une vision 360° des applications", "qualificationsBasic" : "Solide expérience autour de la stack Elastic, Bonne maîtrise des concepts : logs, métriques, traces, Expérience en environnements hybrides, Sensibilité aux enjeux de sécurité et de conformité, Excellentes capacités de communication et de vulgarisation, À l’aise dans des environnements complexes et transverses", "qualificationsPreferred" : "Kubernetes est un plus", "remoteFriendly" : false, "workSiteFlexibility" : "Onsite", "rawDescription" : "Nous sublimons votre expérience. Digitalement. SQLI , leader européen de l'expérience client et de la transformation digitale, accompagne les grandes marques internationales dans la création de valeur grâce à la technologie et à l'innovation numérique. De la stratégie au déploiement des solutions technologiques de nos clients, nous concevons et développons des architectures robustes et performantes, ainsi que des expériences captivantes, en combinant technologies de pointe, méthodologies éprouvées et expertise technique pointue. Pour renforcer nos équipes (2 200 personnes réparties dans 12 pays), nous recrutons des personnes passionnées qui partagent nos valeurs : créativité, engagement et vision d'avenir. Dans le cadre d’un programme stratégique de transformation , vous interviendrez sur la refonte complète des pratiques d’observabilité d’un environnement IT critique. L’objectif : construire une vision 360° des applications en centralisant et exploitant logs, métriques et traces au sein de l’écosystème Elastic, dans des environnements hybrides (VM & containers). Vous jouerez un rôle clé à la foistechnique et transverse , en contribuant activement à la structuration des standards et à l’adoption des bonnes pratiques d’observabilité. Vos missions * Concevoir et mettre en œuvre des solutions d’observabilité basées sur la stack Elastic (Elasticsearch, Kibana, Logstash, Beats, APM…) * Définir les standards, l’architecture et les bonnes pratiques associées * Participer à la gouvernance technique et à la structuration du programme * Mettre en place dashboards, alerting et visualisations * Accompagner les équipes dans l’adoption des solutions déployées * Documenter les processus et assurer le partage de connaissances ## Qualifications * Solide expérience autour de la stack Elastic dans un contexte d’observabilité * Bonne maîtrise des concepts : logs, métriques, traces * Expérience en environnements hybrides (VM, containers, Kubernetes est un plus) * Sensibilité aux enjeux de sécurité et de conformité * Excellentes capacités de communication et de vulgarisation * À l’aise dans des environnements complexes et transverses ## Additional Information Ce que nous offrons : * Des opportunités de formation continue pour rester à la pointe des dernières tendances * Un suivi de carrière avec des standards RH : entretien annuel, suivi de mission, etc. * Un environnement de travail dynamique et stimulant, favorisant l'innovation et la collaboration avec des équipes pluridisciplinaires ! \uD83D\uDCE2 Vous pensez que ce poste est fait pour vous ? Transmettez-nous votre candidature.", "summaryDescription" : "Ingénieur Observability – Elastic Stack (H/F) at SQLI. Skills: Elastic Stack, Observability. Concevoir et mettre en œuvre des solutions d’observabilité. Définir les standards, l’architecture et les bonnes pratiques", "postedDate" : "2026-06-15T12:36:29.000", "createdAt" : "2026-06-15T23:57:21.194", "lastUpdated" : "2026-06-16T07:48:09.200", "ingestTimestamp" : "2026-06-15T23:57:21.194", "mongoId" : "6a306b2ff292fd229cfcf981", "processingStatus" : "llm_updated", "llmProcessingStatus" : true, "salaryBand" : "100k-150k", "hasSalary" : false, "allSkills" : [ "Observability", "Logs", "Metrics", "Traces", "Elastic Stack", "Architecture", "Gouvernance technique", "Environnement IT critique", "VM", "Containers" ], "skillCount" : 10, "jobCategory" : "engineering", "jobSubcategory" : "software", "seniorityLevel" : "Senior", "dataQualityScore" : 1.0, "daysOld" : 0, "hasLocation" : true, "hasGeo" : true, "llmIndustry" : "Technology", "llmIndustryConfidence" : 0.95 } ], "status" : 200, "message" : "observability practices monitoring alerting logging distributed tracing jobs", "metadata" : { "title" : "observability practices monitoring alerting logging distributed tracing" }, "pagination" : { "page" : 0, "limit" : 50, "totalCount" : 4781, "totalPages" : 96, "hasNext" : true, "hasPrevious" : false } }

Remote Observability Practices Monitoring Alerting Logging Distributed Tracing Jobs

Top Skills

Monteur Tracing

Uitvoerder Elektrische Tracing

Executive Assistant, AWS Monitoring and Observability

Standards & Practices Content Analyst

DevOps/Observability Engineer

DevOps/Observability Engineer

Monitoring Engineer

SRE - Observability Expert

Senior Software Engineer, Logging & Experiments

Cardiac Monitoring Tech - Central Monitoring Unit

Condition Monitoring Engineer

Fleet Monitoring Technician

Program Manager, Business Practices

HVAC Monitoring Technician

Observability Platform Engineer

Monitoring / AIOps Engineer

Junior Observability Engineer

Junior Observability Engineer

Junior Observability Engineer

Junior Observability Engineer

Junior Observability Engineer

Junior Observability Engineer

Junior Observability Engineer

Distributed Systems Engineer

Infrastructure Tooling & Observability Engineer

Senior Software Engineer - Distributed Systems

Monitoring Product Marketing Manager

Monitoring Product Marketing Manager

Distributed Training and Inference Engineer

Senior Manager, Engineering - Observability Platform

Research Program Manager, Distributed Research

Staff Product Manager, Agent Observability

Senior Observability Architect

Senior Java Engineer - Distributed Systems - Elasticsearch

Director, Data Governance & Observability

Staff Observability Platform Engineer

Senior Java Engineer - Distributed Systems - Elasticsearch

Principal Observability Platform Engineer

Senior Java Engineer - Distributed Systems - Elasticsearch

Senior Observability Lead

Senior Software Engineer - Observability Visibility

Principal Software Engineer - Distributed Systems - Elasticsearch

Principal Software Engineer - Distributed Systems - Elasticsearch

Software Development Engineer, Observability Insights

Intern - Infrastructure Monitoring Analyst

Director, Data Governance & Observability

Distributed Systems Engineer, Analytical Database Platform

Senior Java Engineer - Distributed Systems - Elasticsearch

Staff Product Manager, Agent Observability

Ingénieur Observability – Elastic Stack (H/F)

Related Searches

All Observability Practices Monitoring Alerting Logging Distributed Tracing Jobs by City

More Remote Jobs

Common Questions