About the Role

The Data Engineer II role focuses on building foundational data systems for an LLM-based insights platform at Amazon's FBA Central Analytics team. Responsibilities include implementing data standardization, governance frameworks, and metadata enrichment to ensure AI-generated outputs are accurate and trustworthy. This position involves designing schema standards, lineage tracking systems, and quality validation frameworks.

Key Responsibilities

• Build dbt-based semantic models representing FBA metrics with business-friendly definitions consumed by RAG
• Automate metadata harvesting with column-level descriptions, ownership tags, and business context for retrieval during text-to-SQL prompts
• Implement lineage tracking tied to Redshift, S3, and Glue to power AI-driven source citations
• Implement fine-grained access controls for embeddings and vector DB access, enforcing compliance
• Build pipelines for proactive quality validation (null checks, distribution anomalies) feeding into AI's feedback loops

Required Skills & Qualifications

Must Have:

• 5+ years of SQL experience
• Experience with data modeling, warehousing and building ETL pipelines
• 5+ years in data engineering with experience in AWS and data quality tooling
• Proficiency in SQL, Python, and workflow orchestration (MWAA/Airflow)

Nice to Have:

• Experience with AWS technologies like Redshift, S3, AWS Glue, EMR, Kinesis, FireHose, Lambda, and IAM roles and permissions
• Experience with non-relational databases / data stores (object storage, document or key-value stores, graph databases, column-family databases)
• Familiarity with LLM-driven metadata retrieval and semantic layer development