Senior Data Scientist, Alexa For Shopping (Rufus)

About the role

We are building an agentic intelligence system that transforms unstructured, noisy customer data into actionable intelligence for product analytics to guide the evolution of Amazon Shopping CX. The system surfaces metrics on demand and insights unprompted, without an analyst in the loop. This role will own multi-agent system orchestration and context management, a self-improving agent layer that gets measurably better over time without human intervention, and reliable signal extraction from unstructured data for proactive intelligence that detects what matters before anyone asks.

Our agentic system is in production. The missing piece is a system that evaluates its own output quality, identifies where it fails, and closes that feedback loop automatically.

Responsibilities

• Own the multi-agent topology (Planner → Worker → Reasoner → Loop Controller), including inter-agent communication protocols and loop termination logic
• Design and manage the context window strategy across agents
• Own all system prompts, routing prompts, and chain-of-thought scaffolding across agents
• Define what "better" means across dimensions (factual grounding, hypothesis novelty, evidence completeness, reasoning coherence) without ground-truth labels at scale
• Design how evaluation signals propagate back into prompt updates and model routing decisions
• Own schema grounding, sparse vector indexing, and domain-scoped kNN queries
• Own embedding strategy, intent classification accuracy, and entity extraction quality
• Operate independently on ill-defined problems, identify and frame research challenges, and deliver end-to-end solutions with significant product impact
• Work directly with the principal engineer, influence the technical roadmap, and partner with software development engineers (SDEs)

Requirements

• 4+ years of data scientist experience
• 5+ years of experience with data querying languages (e.g., SQL), scripting languages (e.g., Python), or statistical/mathematical software (e.g., R, SAS, Matlab)
• Experience with statistical models (e.g., multinomial logistic regression)
• 5+ years of working with Data & AI-related technologies, including AI/ML, GenAI, Analytics, Database, and/or Storage
• Python proficiency: statistical modeling, data manipulation (pandas, numpy, scipy), and scripting across ML pipelines and evaluation infrastructure
• Demonstrated experience extracting structured signal from unstructured text at scale (NLP pipelines, intent classification, entity extraction, or equivalent)

Preferred Qualifications

• Experience with multi-agent system evaluation and end-to-end production RAG or retrieval systems (embedding strategy, vector search, hybrid retrieval, similarity threshold calibration)
• AWS Bedrock or Strands SDK experience, or equivalent orchestration frameworks (LangGraph, CrewAI, AutoGen)
• Graph database experience (Neptune, Neo4j): schema design, traversal queries, knowledge graph construction
• Experience scaling NLP inference pipelines: model sizing decisions, batching strategy, SageMaker or equivalent endpoint optimization
• Business intelligence or analytics domain background: metric definitions, dimensional modeling, causal inference
• Track record of publishing at peer-reviewed venues or presenting at industry conferences

Pay

Base salary range: $159,200 - $215,300 USD annually (USA, WA, Seattle).

Benefits

• Sign-on payments and restricted stock units (RSUs)
• Comprehensive health insurance (medical, dental, vision, prescription, Basic Life & AD&D, with optional supplemental life plans)
• Employee Assistance Program (EAP) and mental health support
• Medical Advice Line
• Flexible Spending Accounts
• Adoption and surrogacy reimbursement coverage
• 401(k) matching
• Paid time off and parental leave

Learn more about our benefits at amazon.jobs/en/benefits.