Agentic AI Engineer

Booz Allen Hamilton•Annapolis Junction, MD

1d•$77,600 - $176,000

About The Position

As an Agentic AI Engineer supporting U.S. Cyber Command cyber operations, you will design, develop, deploy, and maintain AI agents that autonomously execute multi-step workflows, interact with mission systems, and augment cyber operator decision-making. You will apply AI, machine learning, and software engineering technologies to complex operational challenges and contribute to mission-critical solutions. You will collaborate with cyber operators, exploitation and target analysts, systems engineers, and cyber capability developers to deliver scalable, production-ready agentic solutions for distributed environments. This includes developing agent architectures, decision-making logic, memory systems, and orchestration frameworks, and implementing evaluation, monitoring, and governance approaches to support reliable, predictable performance in mission environments. The role also involves helping clients navigate large language models, agentic architectures, AI orchestration frameworks, and autonomous systems for cyber operations and national security missions.

Requirements

5+ years of experience designing and implementing software systems in Python.
Experience creating AI agents or multi-step LLM workflows, including defining agent behavior, sequencing, or state-transition logic.
Experience integrating tools, APIs, or external services into AI-driven or workflow-oriented systems.
Experience building or maintaining memory systems such as session state, long-term persistence, or vector-based retrieval.
Experience implementing inference request flows, including handling latency, token limits, and batching strategies.
Experience writing integration tests for multi-service or multi-component systems.
Knowledge of containerization and CI/CD pipelines.
Knowledge of distributed system patterns such as asynchronous task handling, message routing, or service-based architectures.
Ability to obtain a TS/SCI clearance with a polygraph.
Bachelor's degree in Computer Science, Engineering, or Data Science.

Nice To Haves

Experience architecting multi-agent workflows, including hierarchical, collaborative, or parallel coordination patterns.
Experience implementing state machines, planners, or decision-graph logic for agent behavior and tool routing.
Experience designing agent memory architectures, such as hybrid short-term or long-term memory systems or vector-based semantic recall.
Experience developing evaluation, observability, and monitoring solutions for agentic systems, including traceability of decisions and tool calls.
Experience with orchestration frameworks such as LangGraph, CrewAI, or AutoGen and supporting data stores such as Redis or PostgreSQL.
Experience integrating cloud AI platforms such as AWS Bedrock AgentCore, Google Gemini Enterprise Agent Platform, or Microsoft Foundry Agent Service.
Experience implementing resilience patterns such as retries with backoff, timeouts, circuit breakers, or safe-mode fallbacks for agent behavior.
Experience with Docker, Kubernetes, or infrastructure-as-code tooling.
Excellent written and verbal communication skills.

Responsibilities

Design, develop, deploy, and maintain AI agents for U.S. Cyber Command cyber operations.
Build agents that autonomously execute multi-step workflows, interact with mission systems, and augment cyber operator decision-making.
Apply AI, machine learning, and software engineering technologies to complex operational challenges.
Collaborate with cyber operators, exploitation analysts, target analysts, systems engineers, and cyber capability developers.
Develop agent architectures, decision-making logic, memory systems, and orchestration frameworks.
Implement evaluation, monitoring, and governance approaches to support reliable and predictable agent performance in mission environments.
Help clients navigate large language models, agentic architectures, AI orchestration frameworks, and autonomous systems.