B

Booz Allen

Builds AI and cyber systems for the US government

Agentic AI Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeMcLean, VA, USA$112.8k - $257k /yrIn-person

About the Job

Requirements

  • At least 6 years of software development experience.
  • At least 3 years of experience working in cloud environments, including AWS and Azure, evaluating architectural tradeoffs, designing robust service-based software applications for scalable use, and using LangChain, LangGraph, AutoGen, PydanticAI, CrewAI, or LlamaIndex.
  • Experience with Model Context Protocol (MCP) for tool integration, Agent-to-Agent (A2A) protocol for collaboration, retrieval-augmented generation (RAG) architecture and knowledge graphs, memory architectures for long-running agents such as episodic, semantic, and working memory patterns, and agent benchmarking frameworks such as GAIA, SWE-bench, or custom evaluation harnesses.
  • Experience with tool or function-calling patterns across multiple large language model (LLM) providers.
  • Experience fine-tuning large or small language models (LLMs or SLMs).
  • Knowledge of modern software design patterns, including microservice design or edge computing.
  • Ability to translate agentic AI capabilities into practical enterprise workflows, bridging technical implementation and business-process adoption.
  • Ability to adapt in a rapidly changing environment and navigate ambiguity.
  • Ability to obtain a Secret clearance.
  • A bachelor's degree in Computer Science or Computer Engineering.

Responsibilities

  • Embed agentic AI capabilities into existing enterprise systems and operational workflows, including application programming interface (API) integration, process automation, and end-user adoption.
  • Design and implement intelligent agent architectures that can reason, plan, and take actions.
  • Develop and deploy collaborative multi-agent systems using Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocols.
  • Build advanced retrieval-augmented generation (RAG) pipelines integrating unstructured data with knowledge graphs to enhance reasoning accuracy and context retention.
  • Fine-tune small language models (SLMs) for specific domains and optimize them for edge-device performance.

Desired Qualifications

  • Experience deploying agentic systems in a production environment.
  • Experience deploying agents on edge devices such as Android or using local models.
  • Experience integrating coding agents such as Cursor or Windsurf into an efficient development pipeline with measured results.
  • Programming experience, including machine-learning frameworks such as TensorFlow, PyTorch, llama.cpp, and vLLM.
  • Experience engineering artificial intelligence capabilities in on-premises or multi-classification environments.
  • Verbal and written communication skills for client engagements, client-facing project work, and business development.

About the Company

Booz Allen

Builds AI and cyber systems for the US government

Booz Allen builds and runs technology for the U.S. government, mostly for the military and intelligence agencies, and its engineers work alongside consultants who know each agency's mission. In 1958, it helped the U.S. Navy create PERT, a project-scheduling method first used on the Polaris submarine missile program and later adopted across government and industry. Its teams design cyber defenses, AI and data tools, and battlefield communications, and it sells its own products, such as Vellox, a suite of AI tools that spot and fight off hackers. Agencies pay mainly through multi-year contracts that reimburse costs, bill hours, or set a fixed price. Booz Allen was founded in 1914 and is based in McLean, Virginia.

Company size
10,001+
Company stage
IPO
Headquarters
McLean, VA
Founded
1914

Recently Posted Jobs

Explore more opportunities at Booz Allen

See more jobs