AI Agent Systems Software Engineer, Senior
Phase2 Technology, Corridor North, MD, United States
AI Agent Systems Software Engineer, Senior
United States, Maryland, Annapolis Junction
Apr 22, 2026
Job Number: R0238422
The Opportunity
As an AI software engineer, you have moved past building simple LLM wrappers and into the harder problem of building agents that interact with structured, deterministic systems and produce results that are reliable enough to act on. The real challenge is not getting a language model to generate text, but getting an autonomous system to call the right tools in the right order, translate between natural language and formal representations, and recognize when it has made an error. We are building a platform where AI agents serve as the bridge between human intent and formal computational systems, and we need someone to design and build that bridge.
On this team you will own the AI agent layer that sits between operators and the platform's core reasoning and modeling capabilities. You will design agents that can interpret loosely specified requests, discover relevant computational assets, translate requirements into structured inputs for formal systems, and explain results back to users in actionable language. When the underlying systems reject an input or return an error, your agents must localize the problem, suggest corrections, and help users iterate quickly. You will work with LLMs, tool‑use frameworks, and retrieval systems, always ensuring that the final answers are formally grounded, not merely probabilistic.
You will join a small elite team where everyone operates at the technical frontier. You will make the system accessible by designing agents that let operators interact with formal reasoning and computational modeling through natural language rather than code, in a rapid‑development environment with AI‑native tooling. Success will be measured by whether operators trust and rely on your agents.
Responsibilities
Design and implement AI agents that build on LLMs to provide autonomous tool use, multi‑step reasoning, and retrieval‑augmented generation against structured data and formal systems.
Integrate agents into the platform so that operators can issue low‑level commands via natural language and receive formally grounded outputs.
Localize and mitigate errors when the platform rejects or returns counterexamples, enabling users to iterate quickly.
Collaborate with cross‑functional teams to ensure compliance with security, functional specifications, and maintenance of system availability and reliability.
Qualifications
5+ years of experience designing and implementing software systems.
2+ years of experience with large language models, autonomous agents, or natural language processing applications.
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 similar tooling.
Ability to bridge probabilistic AI outputs with deterministic software expectations to ensure outputs are formally consistent.
Ability to obtain a Secret clearance.
Bachelor’s degree in computer science, artificial intelligence, or computational linguistics.
Nice to Have
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 or national security customers.
TS/SCI clearance with a polygraph.
Master’s degree in computer science or artificial intelligence preferred; Doctorate a plus.
Clearance
Applicants selected will be subject to a security investigation and may need to meet eligibility requirements for access to classified information.
Compensation
Projected annual salary range: $86,800.00 – $198,000.00 (USD). The total compensation package includes health, life, disability, financial, and retirement benefits, paid leave, professional development, tuition assistance, and dependent care support.
Work Model
Remote, hybrid, or onsite options are available depending on the role; employees may be required to work at a Booz Allen or customer facility.
Commitment to Non-Discrimination
All qualified applicants will receive consideration for employment without regard to disability, veteran status, or any other protected characteristic in accordance with applicable federal, state, and local law.
#J-18808-Ljbffr
United States, Maryland, Annapolis Junction
Apr 22, 2026
Job Number: R0238422
The Opportunity
As an AI software engineer, you have moved past building simple LLM wrappers and into the harder problem of building agents that interact with structured, deterministic systems and produce results that are reliable enough to act on. The real challenge is not getting a language model to generate text, but getting an autonomous system to call the right tools in the right order, translate between natural language and formal representations, and recognize when it has made an error. We are building a platform where AI agents serve as the bridge between human intent and formal computational systems, and we need someone to design and build that bridge.
On this team you will own the AI agent layer that sits between operators and the platform's core reasoning and modeling capabilities. You will design agents that can interpret loosely specified requests, discover relevant computational assets, translate requirements into structured inputs for formal systems, and explain results back to users in actionable language. When the underlying systems reject an input or return an error, your agents must localize the problem, suggest corrections, and help users iterate quickly. You will work with LLMs, tool‑use frameworks, and retrieval systems, always ensuring that the final answers are formally grounded, not merely probabilistic.
You will join a small elite team where everyone operates at the technical frontier. You will make the system accessible by designing agents that let operators interact with formal reasoning and computational modeling through natural language rather than code, in a rapid‑development environment with AI‑native tooling. Success will be measured by whether operators trust and rely on your agents.
Responsibilities
Design and implement AI agents that build on LLMs to provide autonomous tool use, multi‑step reasoning, and retrieval‑augmented generation against structured data and formal systems.
Integrate agents into the platform so that operators can issue low‑level commands via natural language and receive formally grounded outputs.
Localize and mitigate errors when the platform rejects or returns counterexamples, enabling users to iterate quickly.
Collaborate with cross‑functional teams to ensure compliance with security, functional specifications, and maintenance of system availability and reliability.
Qualifications
5+ years of experience designing and implementing software systems.
2+ years of experience with large language models, autonomous agents, or natural language processing applications.
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 similar tooling.
Ability to bridge probabilistic AI outputs with deterministic software expectations to ensure outputs are formally consistent.
Ability to obtain a Secret clearance.
Bachelor’s degree in computer science, artificial intelligence, or computational linguistics.
Nice to Have
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 or national security customers.
TS/SCI clearance with a polygraph.
Master’s degree in computer science or artificial intelligence preferred; Doctorate a plus.
Clearance
Applicants selected will be subject to a security investigation and may need to meet eligibility requirements for access to classified information.
Compensation
Projected annual salary range: $86,800.00 – $198,000.00 (USD). The total compensation package includes health, life, disability, financial, and retirement benefits, paid leave, professional development, tuition assistance, and dependent care support.
Work Model
Remote, hybrid, or onsite options are available depending on the role; employees may be required to work at a Booz Allen or customer facility.
Commitment to Non-Discrimination
All qualified applicants will receive consideration for employment without regard to disability, veteran status, or any other protected characteristic in accordance with applicable federal, state, and local law.
#J-18808-Ljbffr