Remote RAG Data Engineer: AI Retrieval Pipelines

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

Job summary

Booz Allen Hamilton is seeking a RAG Data Engineer to build and operate the data ingestion and search infrastructure powering Retrieval-Augmented Generation capabilities. You will design pipelines that transform structured and unstructured information into retrieval-ready assets, enabling AI-powered applications to deliver grounded responses.

You will own ingestion, embedding, and indexing workflows that connect enterprise data sources with Amazon Bedrock and OpenSearch, including document

Qualifications

• Experience developing and maintaining ETL pipelines for structured and unstructured data.
• Experience implementing document normalization, parsing, chunking, and content preparation workflows, and generating embeddings.
• Experience designing and maintaining OpenSearch/Elasticsearch indexes, schemas, mappings, and aliases to optimize search performance.

Responsibilities

• Design and operate data ingestion and search infrastructure for Retrieval-Augmented Generation (RAG).
• Own ingestion, embedding, and indexing workflows connecting enterprise data with Bedrock and OpenSearch.
• Optimize OpenSearch indexes, mappings, shard configurations, and query performance for scalable data retrieval.

Skills

ETL pipelines

Doc normalization

OpenSearch/Elasticsearch

Idempotent ingestion

Metadata modeling

Python

Containerization

Team collaboration

TS/SCI clearance

HS diploma or GED

Education

HS diploma or GED

Tools

Docker

ECS

EKS

Kubernetes

Job description

Booz Allen Hamilton is seeking a RAG Data Engineer to build and operate the data ingestion and search infrastructure powering Retrieval-Augmented Generation capabilities. You will design pipelines that transform structured and unstructured information into retrieval-ready assets, enabling AI-powered applications to deliver grounded responses.

You will own ingestion, embedding, and indexing workflows that connect enterprise data sources with Amazon Bedrock and OpenSearch, including document