RAG Data Engineer

What you'll do

• Build and operate data ingestion and search infrastructure for Retrieval-Augmented Generation (RAG) capabilities.
• Design and maintain pipelines to transform structured and unstructured data into retrieval-ready assets.
• Manage ingestion, embedding, and indexing workflows connecting enterprise data sources to Amazon Bedrock and OpenSearch.
• Implement document normalization, chunking strategies, embedding generation, and metadata enrichment.
• Design and optimize OpenSearch indexes, including mappings, shard configurations, and lifecycle policies.
• Execute reliable upsert, delete, replay, and failure recovery operations for idempotent ingestion processes.
• Track data lineage, versioning, and metadata modeling for enterprise data assets.
• Tune hybrid retrieval systems combining BM25 keyword search and vector similarity search.

What we're looking for

• TS/SCI clearance is required.
• High school diploma or GED is required.
• Experience developing and maintaining ETL or data ingestion pipelines for structured and unstructured data is required.
• Experience implementing document normalization, parsing, chunking, and embedding generation workflows is required.
• Experience designing and maintaining OpenSearch or Elasticsearch indexes, schemas, and mappings is required.
• Experience with Python or other programming languages for data engineering and automation is required.
• Experience with containerized applications such as Docker, ECS, EKS, or Kubernetes is required.
• Experience integrating Amazon Bedrock embeddings into RAG ingestion pipelines (preferred).