Agentic AI Engineer

At Booz Allen Hamilton, this Agentic AI Engineer role supports U.S. Cyber Command cyber operations by building AI agents that can execute multi-step workflows and help augment cyber operator decision-making. You will help deliver mission-focused, production-ready agentic solutions, with an emphasis on reliable performance through evaluation, monitoring, and governance.

The position is based in Annapolis Junction, MD and is offered with a projected annual compensation range of USD 77,600 - 176,000. The work centers on designing and operationalizing agent systems that can interact with mission environments while navigating evolving large language model and orchestration capabilities.

What You’ll Do

• Design, develop, deploy, and maintain AI agents that can autonomously execute multi-step workflows, interact with mission systems, and augment cyber operator decision-making.
• Help set the direction for mission-critical solutions by applying best-fit AI, machine learning, and software engineering to complex operational challenges.
• Build agent architectures including decision-making logic, memory systems, and orchestration frameworks, along with evaluation, monitoring, and governance to support reliable and predictable outcomes in mission environments.
• Collaborate with cyber operators, exploitation analysts, target analysts, systems engineers, and cyber capability developers to deliver scalable, production-ready agentic solutions for distributed environments.
• Navigate rapid advancements in large language models, agentic architectures, AI orchestration frameworks, and autonomous systems to advance capabilities that provide operational advantage in cyberspace.
• Define AI strategy for cyber operations and national security-related missions.

Required Qualifications

• 5+ years of experience designing and implementing software systems in Python.
• Experience creating AI agents or multi-step LLM workflows, including defining agent behavior and 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 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 systems 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.

Technologies

• Python
• CI/CD
• vector-based retrieval
• TS/SCI clearance
• polygraph

Clearance and Security Notice

Applicants selected will be subject to a security investigation and may need to meet eligibility requirements for access to classified information.

Work Model

This role is onsite, with work primarily performed full-time at a customer facility where employees collaborate directly with colleagues and customers as required by the role.

Additional Policies

• Use of artificial intelligence (AI) or other tools to assist with responses during interviews (in-person or virtual) is prohibited unless permission is explicitly provided.
• Selected candidates may be required to complete an identity verification process using advanced biometrics and AI; applicants are expected to be on camera during interviews and assessments. Booz Allen Hamilton may take a picture to verify identity and prevent fraud.

This posting is projected to close within 90 days from the Posting Date. Booz Allen Hamilton provides consideration for employment without regard to disability, status as a protected veteran, or any other status protected by applicable federal, state, local, or international law.