Agentic AI Engineer

Booz Allen Hamilton•Arlington, VA

About The Position

Design, develop, and deliver production-grade agentic AI systems that demonstrate the practical value of generative AI, large language models, and autonomous workflows. The role combines technical expertise and product skills to build AI applications using prompting, retrieval-augmented generation (RAG), agentic orchestration, evaluation pipelines, and human-in-the-loop systems. Architect modular, reusable AI application patterns; integrate cloud-hosted, local, and hybrid model providers; and apply modern GenAI capabilities such as structured prompting, tool use, workflow orchestration, and multimodal reasoning. Design solutions for deployment across cloud-hosted platforms and portable, self-contained builds, optimizing for latency, cost efficiency, observability, and safety. Prototype and iterate using AI-assisted development tools, validating hypotheses through evaluation-driven development and continuous experimentation. Define the direction of mission-critical agentic systems by selecting and combining prompting strategies, RAG architectures, agentic workflows, and fine-tuned or foundation models as appropriate. Collaborate with AI and ML engineers, data engineers, data scientists, solutions architects, and product owners to deliver solutions.

Requirements

At least 1 year of experience designing, developing, or deploying AI-driven systems, including autonomous agents, LLM-based systems, or automated decision pipelines.
At least 1 year of experience with an object-oriented programming language such as Python and applying it to AI and ML solution development.
Experience integrating LLMs, GPT-class models, or multimodal models into applications, pipelines, or mission systems.
Experience with RAG architectures, evaluation methodologies, experimentation workflows, and asynchronous or event-driven programming patterns.
Experience working in cross-functional delivery environments with data scientists, ML engineers, SREs, product managers, and security teams.
Experience creating reference architectures and technical roadmaps.
Secret clearance required.
Bachelor's degree.

Nice To Haves

Experience with agent orchestration frameworks such as LangChain, AutoGen, CrewAI, or custom agent frameworks.
Experience with agent frameworks, interoperability standards, and multi-agent patterns such as MCP, A2A, LangGraph, or equivalent.
Experience with model fine-tuning, prompt tuning, domain adaptation, or reinforcement learning from human or AI feedback.
Experience designing evaluation suites or safety testing frameworks for AI systems.
Experience integrating AI systems with external tools, APIs, or enterprise systems via tool-calling or computer-use patterns.

Responsibilities

Design, develop, and deploy production-grade agentic AI and LLM-based systems.
Architect modular, reusable AI application patterns and solutions.
Integrate cloud-hosted, local, and hybrid model providers into AI applications.
Apply prompting, RAG, agentic orchestration, evaluation pipelines, and human-in-the-loop systems.
Design solutions for cloud-hosted and portable, self-contained deployments, optimizing latency, cost efficiency, observability, and safety.
Rapidly prototype and iterate using AI-assisted development tools.
Validate hypotheses through evaluation-driven development and continuous experimentation.
Select and combine prompting strategies, RAG architectures, agentic workflows, and fine-tuned or foundation models for mission-critical systems.
Collaborate with data engineers, data scientists, solutions architects, product owners, and other AI and ML engineers.