AI Engineer

Booz Allen Hamilton•McLean, VA

11d

About The Position

As an AI / ML Engineer, you recognize that enterprise-grade AI requires thoughtful design, responsible implementation, and precise communication to ensure alignment across mission teams. You enjoy exploring new AI technologies, improving workflows, and translating user needs into well-structured technical solutions. We’re looking for someone with a strong foundation in software development, scripting, automation, systems development, application integration, data engineering, DevOps, IT, or related technical disciplines who can apply that experience to AI / ML-enabled capabilities in sensitive and high-impact environments. As an AI / ML Engineer on our team, you’ll help build and refine multi-step LLM workflows, develop retrieval augmented pipelines, integrate models into operational systems, and perform prompt evaluations to ensure consistency and accuracy. You’ll partner closely with senior technical leaders for guidance while contributing to production-aligned capabilities that support Veteran-facing environments and adjacent mission teams. Work with us to shape real-world AI solutions and accelerate innovation across enterprise systems. Join us. The world can’t wait

Requirements

6+ years of experience in software development, scripting, automation, systems development, data engineering, application integration, DevOps, IT, systems administration, or cloud services
Experience with AI / ML, LLM-enabled applications, prompt engineering, Python-based automation, APIs, data workflows, or emerging technology solutions
Experience designing, testing, and iterating on prompts for production-oriented LLM applications
Experience supporting RAG pipelines, including chunking strategies, embeddings, retrieval tuning, and grounding responses in source data
Experience in Python, including scripting, debugging, writing reusable code, and working with external APIs
Experience with tools for version control and collaborative coding workflows such as Git or Github
Experience creating, troubleshooting, or maintaining functional software components in one or more programming languages
Ability to align stakeholders, clarify requirements, and reduce rework
Ability to obtain and maintain a Public Trust or Suitability/Fitness determination based on client requirements
Bachelor’s degree in a STEM, computer science, information technology, or engineering field

Nice To Haves

Experience with prompting strategies such as few-shot prompting, structured JSON or function calling prompts, or similar prompt design approaches
Experience building or supporting multi-step LLM workflows or agents using LangChain, LlamaIndex, Semantic Kernel, LangGraph, or similar tools
Experience implementing basic guardrails, output validation logic, error handling, or safe handling of model outputs in LLM systems
Experience with vector databases or semantic search, such as pgvector, Azure AI Search, FAISS, or similar tools
Experience evaluating prompts or building regression testing approaches for LLM behavior
Experience with basic SQL, Microsoft SQL Server, or healthcare, claims, or research data
Experience with Azure cloud services or Azure ML / AI Foundry tooling and integrating applications with APIs, databases, cloud services, or enterprise systems
Experience working with PHI / PII or in HIPAA, IRB, or ATO governed environments
Knowledge of responsible AI concepts including bias considerations, validation practices, and safe handling of model outputs
Possession of excellent verbal and written communication skills

Responsibilities

Build and refine multi-step LLM workflows
Develop retrieval augmented pipelines
Integrate models into operational systems
Perform prompt evaluations to ensure consistency and accuracy
Partner closely with senior technical leaders for guidance
Contribute to production-aligned capabilities that support Veteran-facing environments and adjacent mission teams