About this role
Why this role matters Every AI agent, scorecard, and dashboard we deliver is only as good as the data underneath it. As a Data Engineer, you’ll build that foundation: the pipelines, connectors, indexes, vector stores, and data marts that make our AI products accurate, grounded, and auditable.
What you’ll do
- Design and build ingestion pipelines for structured data, unstructured content such as documents and PDFs, and metadata
- Build reusable connectors to enterprise systems, catalogs, content repositories, and licensed third-party sources via APIs
- Model and build raw-to-mart data layers serving both analytics and AI use cases
- Implement metadata extraction, enrichment, and search indexing, including semantic and vector indexes for RAG
- Set up and manage the vector databases and knowledge repositories that power LLM agents
- Build data quality rules, profiling, scoring outputs, and exception handling
- Register lineage and maintain source registries, version tracking, and refresh controls
- Design data stores for signals, findings, audit trails, and user feedback loops
- Apply security and governance controls, including RBAC, PII and sensitivity flagging, and approved data handling
- Support SIT and UAT data validation, defect fixes, and production releases
What you bring
- Strong Python and SQL, with solid dimensional and normalized data modeling
- Hands-on experience with a modern data platform such as Databricks, Snowflake, or Azure/AWS data services
- Pipeline orchestration and transformation with Spark, Airflow, ADF, dbt, or similar
- REST API integration, JSON handling, and incremental or CDC ingestion patterns
- Data quality frameworks and pipeline testing practices
- Git and CI/CD for data workloads
Bonus points for
- RAG data preparation: chunking, embeddings, and vector databases (Azure AI Search, pgvector, Pinecone, or similar)
- Unstructured content processing, including text extraction, OCR, and document parsing
- Metadata management, data catalogs, ontologies, or knowledge graphs such as Neptune
- Experience supporting LLM or agentic applications with grounded, traceable data
- Life sciences data exposure and experience handling regulated data
- Azure Data Engineer, Databricks, AWS, or Snowflake certification