Ruby Labs
tech
SeniorAIEngineer(Node.js/Next.js/TypeScript)
Neural analysis suggests this role is
optimal for Senior candidates.
“Senior AI Engineer (Node. js / Next. js / TypeScript) at Ruby Labs. Skills: AI Infrastructure, Prompt Engineering, Structured Outputs, LLM Workflows, LangChain, LlamaIndex, Langfuse, OpenRouter, Model Performance, Reliability, Cost Efficiency, Observability, Evaluation, Node. js, Next. js, TypeScript. Advance AI infrastructure. Focus on model performance, reliability, and cost efficiency”
What You'll Achieve.
Consistently improve model quality and operational efficiency; Drive key AI features from early experimentation all the way through to production; Maximize generation quality and reasoning; Ensure AI outputs are predictable and ready for seamless integration into application logic; Collect feedback and score the quality of responses in real time; Optimize for cost, latency, and context window usage; Make deployment decisions for new prompts or models strictly based on quantitative benchmarks and trace data; Identify root causes of hallucinations or logic errors; Meet specific domain requirements
Industry & Context.
Deep debugging of complex LLM chains; Identify bottlenecks; Optimize for cost, latency, and context window usage; Analyze results based on quantitative metrics; Identify root causes of hallucinations or logic errors
Located within approximately ± 4 hours of CET
What They're Looking For.
Must Have
Node. js & Next. js: Deep knowledge of the stack to build reliable services and handle complex LLM-generated data., Dynamic Prompting Skills: Proven experience in building prompts where content is highly dependent on input variables and context injection., OpenRouter Experience: Experience working with unified APIs, managing rate limits, and selecting the most cost-effective models for specific tasks., Langfuse (or similar): Understanding of LLM observability principles — setting up tracing, creating test datasets, and integrating scoring systems., Evaluation Methodology: Experience with frameworks like RAGAS or building custom “LLM-as-a-judge” systems., Analytical Mindset: Ability to transform raw generation logs into actionable business metrics and technical insights., Iterative Mindset: Focus on continuous product improvement through constant feedback loops., Fluency in Russian and/or Ukrainian.
Nice to Have
Fine-Tuning: Practical experience in fine-tuning models for specific domain tasks or JSON compliance., RAG Architecture: Understanding how to build and optimize Retrieval-Augmented Generation systems, including indexing, retrieval, and re-ranking., Python: Basic knowledge for working with data science scripts or AI evaluation libraries.
What You'll Do.
Advance AI infrastructure
Focus on model performance
Take ownership of prompt systems
Cover observability and evaluation using Langfuse and AI gateways
Consistently improve model quality and operational efficiency
Drive key AI features from early experimentation to production
dynamic prompt templates with conditional logic
Efficiently reuse information and context within prompts
Implement various response schemes (JSON mode
Build robust evaluation pipelines
Use Langfuse to collect feedback and score response quality in real time
Perform deep debugging of complex LLM chains using Langfuse traces
Run systematic experiments across different models via OpenRouter
Analyze results based on quantitative metrics
Make deployment decisions for new prompts or models based on quantitative benchmarks and trace data
Develop scoring systems to analyze the “Problem → Solution” chain
Identify root causes of hallucinations or logic errors using Langfuse analytics
Regularly re-evaluate model performance
Perform fine-tuning when necessary
How You'll Work.
Team & Collaboration
Optimal collaboration and communication during working hours (within ± 4 hours of CET)
Full Job Description
ABOUT US Ruby Labs is a leading tech company that creates and operates innovative consumer products. We offer a diverse range of opportunities across the health, education, and entertainment industries. Our innovative teams are driving the future of consumer-led products, and we're always looking for passionate individuals to join us. Learn more about our story at: https://rubylabs.com/about-us/ ABOUT THE ROLE We are looking for a Senior AI Engineer (Node.js / Next.js / TypeScript) to join our team and help advance our AI infrastructure. You'll work within a modern tech stack, focusing on model performance, reliability, and cost efficiency. You'll take ownership of prompt systems, structured outputs, and LLM workflows built on LangChain or LlamaIndex. The role also covers observability and evaluation using Langfuse and AI gateways such as OpenRouter, with the goal of consistently improving model quality and operational efficiency. You'll drive key AI features from early experimentation all the way through to production. KEY RESPONSIBILITIES - Advanced Prompt Engineering: Designing complex, dynamic prompt templates with conditional logic and efficiently reusing information and context within prompts to maximize generation quality and reasoning. - Structured Outputs & Schemas: Implementing various response schemes (JSON mode, function calling, Zod/JSON schemas) to ensure AI outputs are predictable and ready for seamless integration into application logic. - Prompt Engineering & Evaluations: Building robust evaluation pipelines and using Langfuse to collect feedback and score the quality of responses in real time. - Tracing & Debugging: Performing deep debugging of complex LLM chains using Langfuse traces to identify bottlenecks and optimize for cost, latency, and context window usage. - AI A/B Testing: Running systematic experiments across different models via OpenRouter (e.g., comparing Claude 3.5 Sonnet vs. GPT-4o) and analyzing results based on quantitative metrics
Applying for this Senior AI Engineer (Node. js / Next. js / TypeScript) role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Ashby
- Ashby is a fast modern ATS — most applications take under 3 minutes.
- The resume parser is strong; verify parsed experience dates and job titles.
- Custom screening questions are often scored algorithmically — answer completely.
- Location field affects geo-based screening; use your actual metro area.
ANONYMOUS · UNFILTERED
What do employees actually say about Ruby Labs?
Real rants from real employees. Read before you apply.