Lead AI Engineer

Bigbear.ai•UNAVAILABLE, UNAVAILABLE

About The Position

BigBear.ai is seeking a Lead AI Engineer to drive the design, development, and deployment of generative AI and agentic systems for mission-critical Department of War operations. The role combines hands-on engineering with technical leadership: setting AI architecture direction, leading and mentoring engineers, and working with government stakeholders to translate operational needs into production-ready AI capabilities. The Lead AI Engineer owns the technical direction of AI-enabled solutions from discovery through deployment. The role collaborates with data scientists, systems analysts, product managers, and mission users to deliver AI systems that meet high standards for performance, reliability, and security. Applicants must currently reside in the United States.

Requirements

Bachelor’s degree in computer science, software engineering, or a related field, with 15 years of experience.
Demonstrated experience leading engineering teams or serving as technical lead on complex software initiatives.
Hands-on experience designing and deploying generative AI or agentic AI systems in operational or production environments.
Experience with multi-agent orchestration, RAG, prompt engineering (including few-shot and chain-of-thought), and LLM API integration.
Proficiency in front-end and back-end development.
Experience with Python, .NET/C#, Angular, TypeScript, Docker, AWS services, SQL Server, web/data pipelines, and Git-based CI/CD, or equivalent technologies. Examples of equivalents include React for Angular, Java for .NET, PostgreSQL for SQL Server, and Azure for AWS.
Experience delivering software in secure, regulated environments, including ATO, FedRAMP, and security hardening.
Strong analytical and problem-solving skills, with a focus on delivering high-quality, mission-ready solutions.
Ability to explain AI capabilities, limitations, and trade-offs clearly to technical and non-technical stakeholders.
Must currently reside in the United States.

Nice To Haves

Experience building custom Model Context Protocol (MCP) servers.
Experience with AI-assisted development tools such as Claude Code, Cursor, or Copilot Agents.
Experience with Helm/YAML, GitLab, Qlik, or Databricks.
Experience building AI evaluation frameworks or conducting adversarial testing of LLM systems.
Background in data warehousing, ETL, or business intelligence.
Experience integrating AI into enterprise workflow tools, such as Power Automate custom connectors.

Responsibilities

Define and lead architecture for generative AI solutions, including multi-agent workflows, retrieval-augmented generation (RAG), and LLM integration; establish engineering standards and best practices.
Design, build, and deploy multi-agent orchestration and custom Model Context Protocol (MCP) servers that securely connect AI agents to enterprise and mission systems.
Build applications using commercial and government-approved LLM endpoints, applying prompt engineering, dataset routing, and confidence gating to improve output quality and reliability.
Engage government stakeholders to gather requirements, assess feasibility within time and cost constraints, and rapidly prototype solutions.
Design, develop, document, test, and debug full-stack applications across front-end, back-end, API, and data layers.
Shape and implement cloud-forward data environments and web/data pipelines for AI workflows, including document ingestion, classification, and knowledge-domain routing.
Build evaluation harnesses for regression testing, citation verification, and retrieval transparency; red-team AI systems for prompt injection and adversarial failure modes; ensure compliance with DoW security requirements, including ATO and FedRAMP.
Lead and mentor engineers on AI tooling, AI-first development practices, and adoption strategies; promote collaboration through hackathons and knowledge sharing.
Share field-discovered gaps and user feedback with product leadership and contribute to roadmap, release planning, and prioritization.
Coordinate system installations, monitor production performance, and ensure deployed AI capabilities meet specifications and mission expectations.