- Build and maintain data pipelines feeding NLQ, semantic search, and knowledge graph capabilities on the SEC's Enterprise Data Platform
- Onboard new data sources and extend the semantic layer without disrupting existing live pipelines
- Ingest, transform, and deliver XBRL and SEC financial filing datasets
- Support GraphRAG and knowledge graph pipelines alongside the Data Architect
- Work with AWS data services including Athena, DataZone, SageMaker, S3, and Lambda
- Implement and maintain vector database and semantic search tooling
- Own metadata management, data lineage, and data quality validation across the pipeline ecosystem
- Monitor pipeline health and resolve data integration issues across environments
- Ensure all work meets federal security and compliance requirements
PostgreSQLPythonSQL+1 more