RAG Application Engineer

Booz Allen Hamilton•Fort Meade, MD

1d•$69,400 - $158,000

About The Position

The RAG Application Engineer builds and maintains the runtime application layer for Retrieval-Augmented Generation (RAG) systems, integrating search, models, and metadata into a coherent experience. The role implements end-to-end query workflows—including embedding generation, hybrid retrieval, reranking, citation assembly, and request-level guardrails—to provide analysts with grounded, high-quality responses at scale. The engineer develops API endpoints, manages model integrations, enforces authentication and authorization, and implements robust retry, timeout, and error-handling strategies in a secure, cloud-based environment. The role also containerizes services and collaborates with Cloud, Security, Data, and Site Reliability Engineering teams to make the RAG runtime stable, secure, observable, and ready for mission use.

Requirements

Experience building back-end or platform services using programming languages such as Python or Java.
Experience designing or integrating RAG workflows, including embeddings, hybrid retrieval, vector search, and reranking.
Experience implementing API request pipelines, orchestration logic, and service routing for AI model and search calls.
Experience enforcing authentication and authorization within service logic.
Experience developing resilient services with retry, backoff, timeout, and error-handling strategies.
Experience collaborating with data, search, cloud, and security engineers to optimize retrieval behavior.
Experience containerizing applications using Docker and deploying to ECS, EKS, or Kubernetes.
Experience building telemetry, including structured logs, metrics, and traces.
Ability to translate RAG requirements into clean, maintainable application logic.
TS/SCI clearance.
High school diploma or GED.

Nice To Haves

Experience integrating Amazon Bedrock model inference into application workflows.
Experience implementing hybrid retrieval with OpenSearch, including BM25 and vector search.
Experience developing citation assembly logic, grounding validation, or model guardrails.
Experience designing API gateways, rate limiting, caching, or other high-availability patterns.
Experience working with message queues or asynchronous workflows, including Kafka or Amazon SQS.
Experience contributing to evaluation data pipelines or partnering with evaluation scientists.
Experience using infrastructure-as-code frameworks such as Terraform, CloudFormation, or AWS CDK.
Ability to collaborate across multiple engineering disciplines.
Excellent communication skills.

Responsibilities

Build and maintain RAG runtime application logic and end-to-end query workflows.
Implement embedding generation, hybrid retrieval, reranking, citation assembly, and request-level guardrails.
Develop API endpoints and manage integrations with AI models and search services.
Enforce authentication and authorization controls within service logic.
Implement resilient retry, backoff, timeout, and error-handling strategies.
Containerize applications and deploy them to ECS, EKS, or Kubernetes.
Build telemetry using structured logs, metrics, and traces.
Collaborate with Cloud, Security, Data, and Site Reliability Engineering teammates to optimize retrieval behavior and ensure runtime stability, security, and observability.