RAG Data Engineer: Ingest, Embeddings & OpenSearch

Booz Allen; Annapolis (MD); On-site; USD 62,000 - 141,000; Full time

Job summary

Booz Allen is seeking a RAG Data Engineer to build and operate ingestion and search pipelines that power enterprise retrieval augmented generation. You will own embeddings, indexing workflows, and OpenSearch tuning, collaborating with cloud, security, and AI teams in a mission-driven environment.

The role requires TS/SCI clearance with polygraph and a HS diploma or GED, with on-site work in Annapolis Junction, MD. A strong background in containerized deployments and Python is essential.

Qualifications

• Experience building ETL/data ingestion pipelines for structured and unstructured data.
• Experience implementing document normalization, parsing, chunking, and content prep with embeddings.
• Experience designing and maintaining OpenSearch/Elasticsearch indexes, schemas, mappings, aliases, and tuning queries.
• Experience with idempotent ingestion: upsert, delete, replay and failure recovery.
• Experience with metadata modeling, enrichment, lineage, and version tracking.
• Proficient in Python or other data engineering languages.
• Experience with containerized deployments (Docker/ECS/EKS/Kubernetes).
• Ability to collaborate with cross-functional teams (engineering, security, cloud,应用开发).
• TS/SCI clearance with polygraph required.
• HS diploma or GED required.

Responsibilities

• Build and operate data ingestion and search infrastructure powering RAG capabilities.
• Design, implement, and maintain pipelines for structured and unstructured data; generate embeddings and connect to Bedrock/OpenSearch.
• Own ingestion, embedding, and indexing workflows; ensure data lineage and upsert/delete reliability.
• Design OpenSearch indexes, mappings, shard configs, and performance tuning.
• Collaborate with cloud security and application teams to ensure scalable, secure data retrieval foundation.

Skills

ETL pipelines

Document normalization

OpenSearch indexes

Idempotent ingestion

Metadata modeling

Python

Containerization

Team collaboration

TS/SCI clearance

High school diploma

Education

HS diploma or GED

Tools

Docker

ECS

EKS

Kubernetes

Job description

Booz Allen is seeking a RAG Data Engineer to build and operate ingestion and search pipelines that power enterprise retrieval augmented generation. You will own embeddings, indexing workflows, and OpenSearch tuning, collaborating with cloud, security, and AI teams in a mission-driven environment.

The role requires TS/SCI clearance with polygraph and a HS diploma or GED, with on-site work in Annapolis Junction, MD. A strong background in containerized deployments and Python is essential.