Agentic AI Engineer at 631 Booz Allen Hamilton_United States — Annapolis Junction, MD

Agentic AI EngineerThe Opportunity:

As an Agentic AI Engineer, you will design, build, and deploy AI agents capable of autonomously using tools, interacting with software systems, and executing multi-step tasks. You will develop agent architectures, including decision-making logic, memory systems, and orchestration flows that enable AI agents to perform complex operations reliably and safely. You will integrate new and existing tools, define structured interfaces for agent interactions, and implement evaluation and monitoring approaches to ensure agent behavior remains predictable and aligned with mission needs. You’ll collaborate across engineering teams to deliver scalable and production-ready agentic systems that enhance capabilities across distributed environments.

You Have:

• 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
• TS/SCI clearance with a polygraph
• Bachelor’s degree in Computer Science, Engineering, or Data Science

Nice If You Have:

• Experience architecting multi-agent workflows, including coordination patterns such as hierarchical, collaborative, or parallel tasking
• 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/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 Postgres
• 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
• Possession of excellent written and verbal communication skills

Clearance:

Compensation

Identity Statement

Candidate AI Usage Policy

• Remote: If this position is listed as remote, there may still be occasions when you are required to work in person at a Booz Allen or customer facility.
• Hybrid: If this position is listed as hybrid, you will be expected to work from a Booz Allen facility frequently, in alignment with leadership expectations and the needs of the role. You may also be required to work from or visit a customer facility.
• Onsite: If this position is listed as onsite, work will primarily be performed at a Booz Allen office or customer facility, where employees will collaborate directly with colleagues and customers as required by the role.

Commitment to Non-Discrimination