AI Agent Systems Software Engineer, Senior

Booz Allen Hamilton•Washington, DC

3d•$86,800 - $198,000•Remote

About The Position

As an AI software engineer, you will move beyond simple LLM wrappers to build agents that interact with structured, deterministic systems, producing reliable and actionable results. The core challenge involves enabling autonomous systems to call the right tools in the correct order, translate between natural language and formal representations, and identify errors. This role is crucial for a platform where AI agents bridge human intent and formal computational systems. You will own the AI agent layer, designing agents that interpret loosely specified requests, discover computational assets, translate requirements into structured inputs for formal systems, and explain results to users. When systems reject inputs or return counterexamples, your agents will localize errors, suggest corrections, and facilitate quick iteration. You will utilize LLMs, tool-use frameworks, and retrieval systems, ensuring all final answers are formally grounded, not probabilistically generated. Joining a small, elite team, you will operate at the technical frontier, making the system accessible by designing agents that allow operators to interact with formal reasoning and computational modeling through natural language. You will build in a rapid development environment with AI-native tooling, with success measured by operator trust and confidence in your agents.

Requirements

5+ years of experience designing and implementing software systems
2+ years of experience on applications involving large language models, autonomous agents, or natural language processing
Experience building agentic systems that use tool calling, multi-step reasoning, or retrieval-augmented generation to interact with external APIs or structured data sources
Experience with LLM orchestration frameworks such as LangGraph, LangChain, or agent-coordination tooling
Ability to work across the boundary between probabilistic AI systems and deterministic software, ensuring that LLM outputs conform to the expectations of formal or structured downstream systems
Ability to obtain a Secret clearance
Bachelor's degree in computer science, artificial intelligence, or computational linguistics

Nice To Haves

Experience translating natural language specifications into formal or semi-formal representations such as constraint sets, typed schemas, or domain-specific intermediate languages
Experience building human-in-the-loop AI workflows where the system proposes actions and a human approves, modifies, or rejects them
Experience deploying or fine-tuning language models in secure or air-gapped environments for defense, intelligence, or national security customers
TS/SCI clearance with a polygraph
Master's degree in computer science or artificial intelligence preferred
Doctorate degree in computer science or artificial intelligence a plus

Responsibilities

Design and build AI agents that serve as the bridge between human intent and formal computational systems.
Own the AI agent layer that sits between operators and the platform's core reasoning and modeling capabilities.
Design agents that can interpret loosely specified requests.
Discover relevant computational assets.
Translate requirements into structured inputs that formal systems can evaluate.
Explain results back to users in language they can act on.
Localize errors, suggest corrections, and help users iterate quickly when underlying systems reject an input or return a counterexample.
Work with LLMs, tool-use frameworks, and retrieval systems, ensuring that final answers are formally grounded, not probabilistically generated.
Make the system accessible by designing agents that let operators interact with formal reasoning and computational modeling through natural language rather than code.
Build in a rapid development environment with AI-native tooling.