Senior Data Engineer

About the role

Position Summary...

What you'll do... What you'll do:

-

Design, build, test, and deploy scalable, intelligent data solutions that support millions of Sam’s Club customers—while laying the groundwork for Agentic AI systems that consume and act on this data.

-

Partner with engineering, AI/ML, and product teams to ensure data services are discoverable, trustworthy, and consumable by next-gen AI agents and LLM-based systems.

-

Collaborate across Sam’s Club engineering teams to contribute to a data-first, agent-aware architecture and foster a culture of innovation around intelligent automation.

-

Engage with Product Management and Business teams to prioritize data products that will drive autonomous decision-making and context-rich recommendations.

-

Build features that enable seamless integration between structured/unstructured data and downstream AI agents, enabling smarter responses, faster insights, and automation.

-

Deploy and monitor products on cloud platforms with agent observability, telemetry, and auditability in mind.

-

Develop and implement best-in-class data health monitoring, traceability, and context enrichment processes to ensure data used by agents is reliable and governed.

-

Lead technical solutioning for full-lifecycle projects, with an eye on how data will power autonomous workflows, co-pilots, and multi-agent systems.

What you'll bring:

-

4–6 years of experience in Big Data development with a focus on scalable, fault-tolerant architectures.

-

2–3 years of hands-on experience with cloud platforms such as GCP or Azure, including services like BigQuery, Dataflow, Pub/Sub, or equivalent.

-

Strong foundation in data engineering best practices and experience building complex data pipelines optimized for agent consumption.

-

Experience designing and implementing semantic layers or knowledge graphs that could power data-aware AI agents.

-

Proven experience in data modeling and architecture, with awareness of how data structures affect retrieval quality and contextual relevance for agents.

-

Exposure to LLM-driven workflows, prompt templating, or orchestration tools (e.g., LangChain, LlamaIndex, CrewAI) is beneficial but not required.

-

Understanding of data governance, including quality, access control, and lineage—especially in the context of agent auditability and trust.

-

Experience writing clean, testable code in Python, Java, or Scala; experience with PySpark/Spark for distributed data processing.

-

Demonstrated ability to write optimized, scalable SQL and to work with large datasets across cloud-native and open-source platforms.