Amazon.com Services LLC
Applied Science, Advertising
AppliedScientistII,DemandEnablement,ProductAnalyticsandOperations
Neural analysis suggests this role is
optimal for Mid candidates.
“Applied Scientist II, Demand Enablement, Product Analytics and Operations at Amazon.com Services LLC. Skills: Multi-agent systems, LLM architectures, Production ML, Data analytics. Design intelligent systems. Build intelligent systems”
What You'll Achieve.
Reduce advertiser escalation time
Industry & Context.
Root cause analysis; Troubleshooting; Anomaly isolation
What They're Looking For.
Must Have
3+ years building models, Master's degree and 4+ years experience, PhD, Experience programming in Java, Experience programming in C++, Experience programming in Python, Experience in algorithms, Experience in data structures, Experience in parsing, Experience in numerical optimization, Experience in data mining, Experience in parallel computing, Experience in distributed computing, Experience in high-performance computing
Nice to Have
Deep learning algorithms experience, Computer vision algorithms experience, Professional software development experience, Designing experiments experience, Statistical analysis of results experience
What You'll Do.
Design intelligent systems
Build intelligent systems
Automate root cause analysis
Architect agentic orchestration patterns
Develop hierarchical analysis frameworks
Build self-learning feedback loops
Conduct deep data analysis
Derive insights for business
Uncover new opportunities
Develop machine learning models
Develop optimization strategies
Solve business problems
Perform statistical analysis
Optimize advertiser experiences
Collaborate with software engineers
Deliver end-to-end solutions
Research machine learning models
Implement machine learning models
Improve advertising performance
Review system escalations
Identify reasoning errors
Adjust orchestration logic
Write evaluation cases
Design agent architectures
Invoke sub-agents as tools
Build analysis frameworks
Develop self-learning loops
Keep diagnostic knowledge current
Work with product managers
Work with support teams
Resolve advertiser issues
Measure recommendation effectiveness
Prototype anomaly detection
Contribute to evaluation science
How You'll Work.
Team & Collaboration
Software engineers; Product managers; Support teams; Cross-functional teams
Communication Scope
Translate complex behaviors
Full Job Description
In this role, you will design and build intelligent multi-agent systems that automate root cause analysis for advertising campaign delivery at scale. You will architect agentic orchestration patterns where specialized sub-agents (campaign diagnostics, deal-level troubleshooting, pacing control) are invoked as composable tools by a reasoning layer that determines which subsystems to query based on the nature of the issue. You will develop hierarchical analysis frameworks that move from daily trend detection to intra-day anomaly isolation, enabling the system to pinpoint when and why delivery degraded rather than relying on static time windows. You will build self-learning feedback loops where the system identifies recurring failure signatures (auction dynamics, pacing anomalies, supply contention), updates its diagnostic knowledge as engineering teams deploy fixes, and retires stale patterns automatically. We are looking for a passionate Applied Scientist with technical expertise in LLM-based agent architectures, retrieval-augmented generation, time-series anomaly detection, and production ML systems. In addition to hands-on experience building agentic AI solutions, an ideal candidate should demonstrate the ability to translate complex distributed system behaviors into structured diagnostic reasoning, show a willingness to push the boundaries of how LLMs interact with real-time operational data, and thrive in an environment where you ship production systems that directly reduce advertiser escalation time from days to minutes. Key job responsibilities * Conduct deep data analysis to derive insights for the business, identify gaps, and uncover new opportunities. * Develop scalable and effective machine learning models and optimization strategies to solve business problems. * Run regular A/B experiments, gather data, and perform statistical analysis to optimize advertiser experiences. * Collaborate closely with software engineers to deliver end-to-end solutions into pro
Applying for this Applied Scientist II, Demand Enablement, Product Analytics and Operations role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
ANONYMOUS · UNFILTERED
What do employees actually say about Amazon.com Services LLC?
Real rants from real employees. Read before you apply.