Responsibilities
- Contribute to end-to-end delivery of agentic, full-stack systems from prototype to production, embedded alongside defense and intelligence customers.
- Build and deploy ML services leveraging LLMs, embeddings, RAG, and agent orchestration into production environments, including classified and air-gapped ones.
- Work directly with customers to understand problems, support delivery sequencing, and ship AI applications under real-world constraints.
- Help codify repeatable patterns into reusable tools and building blocks that help the team ship faster.
Requirements
- Experience in the defense or intelligence fields.
- Ability to contribute to solutions across the full LLM stack, from the OS, storage, and network up to the API and transport layer.
- Use AI coding tools (Claude Code, Cursor, Copilot) daily and instinctively.
- Leverage LLMs across the development lifecycle, and stay current with emerging models and tooling.
- Working knowledge of modern agent frameworks and SDKs (LangGraph, OpenAI Agents SDK, Claude Agent SDK, AutoGen, or similar).
- Familiarity with MCP or similar LLM integration frameworks.
- Clear-eyed view of AI limitations; know when to trust AI-generated output and when to verify.
Nice to Have
- Familiarity with infrastructure management (Docker, Kubernetes, AWS).
- Exposure to encryption, authentication, Linux systems administration, DevOps, or SRE.
- Any production experience with agentic services or forward-deployed AI applications.
- Experience in a customer-facing or embedded delivery role.
- Exposure to federated or privacy-preserving data architectures.
Compensation
Competitive salary and equity compensation.
Additional Information
- Location: This role is based in the DC/Metro area; remote candidates will be considered with 25% travel expected.
- Clearance Requirement: An active U.S. Government clearance is strongly preferred, but we are open to clearance eligible candidates.
