AI Engineer

Booz Allen Hamilton•McLean, DC

7d•Remote

About The Position

Join a hands-on AI engineering team building and deploying LLM-powered applications. In this role, you’ll implement core components of AI systems, including prompting, retrieval pipelines, and API integrations, while gaining experience with the tooling and infrastructure required to run AI workloads in production. You'll work across the full AI application lifecycle from data ingestion and retrieval to prompt engineering, evaluation, deployment, and production operations building secure, mission-focused AI solutions for federal clients. Join us. The world can’t wait.

Requirements

1+ years of experience in software engineering, data engineering, or applied AI / ML.
Experience building applications in Python using frameworks such as FastAPI or Flask.
Experience building and integrating applications using LLM APIs such as OpenAI, AWS Bedrock, or Azure OpenAI.
Experience implementing Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embeddings, retrieval workflows, and prompt augmentation.
Experience with vector databases such as FAISS, Pinecone, Weaviate, or OpenSearch Vector Search.
Experience with cloud environments, including AWS services such as S3, Lambda, EC2, IAM, and CloudWatch.
Experience using Git, basic CI/CD pipelines, and containerization with Docker.
Experience designing or consuming REST APIs and working with structured outputs such as JSON schemas and function or tool calling.
Knowledge of prompt engineering, prompt evaluation, and common LLM failure modes, including hallucinations, prompt injection, data leakage, jailbreak attempts, and grounding techniques.
Knowledge of prompt evaluation techniques and response quality testing.
Ability to obtain a TS/SCI clearance.
Bachelor's degree.

Nice To Haves

Experience with orchestration frameworks such as LangChain or LlamaIndex.
Experience with embeddings via OpenAI, Cohere, or SentenceTransformers.
Experience with monitoring and logging tools such as CloudWatch or Datadog.
Experience deploying services using Docker Compose or Kubernetes.
Experience with structured logging and debugging distributed API failures.
Experience with AWS Secrets Manager or AWS Systems Manager Parameter Store.
Experience with asynchronous Python programming or background processing.
Experience with Model Context Protocol (MCP) or modern AI tool integration standards.

Responsibilities

Implement core components of AI systems, including prompting, retrieval pipelines, and API integrations.
Gain experience with the tooling and infrastructure required to run AI workloads in production.
Work across the full AI application lifecycle from data ingestion and retrieval to prompt engineering, evaluation, deployment, and production operations.
Build secure, mission-focused AI solutions for federal clients.