Senior Data Engineer, Amazon Customer Service

How often have you had an opportunity to be a member of a team that is tasked with solving customer needs through disruptive and innovative technology? Everyone on the team needs to be entrepreneurial, wear many hats and work in a fast-paced, ambiguous, and highly collaborative environment that’s more startup than big company. If this sounds intriguing, then we’d like to talk to you about a role on the Amazon Defect Elimination Analytics team. This team drives Amazon towards a defect-free customer experience by building technology that rapidly identifies defects, associates them with the information required to resolve the root cause, and prioritizes the multitude of improvement opportunities based on business and customer needs. To continue expanding our defect elimination program, we seek a passionate, results-oriented, Senior Data Engineer.

- Design, develop and maintain scaled, automated, user-friendly systems, reports, dashboards, etc.

- Partner with operations/business teams/economist/ML teams to consult, develop and implement KPI's, automated reporting/process solutions and data infrastructure improvements to meet business needs.

- Build and maintain data infrastructure for AI agent systems, including vector databases, embedding pipelines, and retrieval-augmented generation (RAG) data stores.

- Design data architectures that enable agentic workflows - structured data access layers, tool-use APIs, context management systems that AI agents consume autonomously, self-serve analytics.

- Develop observability and evaluation pipelines for LLM-powered features, including tracking model performance, hallucination rates, latency, and cost metrics at scale.

- Apply analytic skill to extract meaningful insights and learnings from large and complicated data sets, including unstructured text corpora used for generative AI applications.

- Serve as liaison with Business and technical teams to achieve project objectives, requiring data gathering, problem solving, modeling, and communication of insights and recommendations.

- Stay current with advances in AI/ML data infrastructure (e.g., feature stores, vector search, streaming inference pipelines) and evaluate their applicability to defect elimination use cases.