LLM · agentic AI
ABOUT THE ROLE
Build and deploy production-grade agentic AI systems for high-impact government missions. This hands-on engineering role combines developing AI systems from prototype through deployment with direct collaboration with government partners.
WHAT YOU'LL DO
- Build and deploy LLM-powered agentic systems, including multi-agent, retrieval-augmented generation, and human-in-the-loop workflows.
- Work with government partners to translate mission needs into practical technical systems.
- Design and maintain data curation, evaluation, and machine learning infrastructure pipelines.
- Own systems through architecture, implementation, deployment, reliability, and iteration.
- Create new AI systems that turn mission data and models into operational capabilities.
WHAT WE'RE LOOKING FOR
- Up to 10 years of relevant experience, with hands-on engineering experience in AI/ML, software, or solutions engineering.
- Strong Python skills and experience with TypeScript, ideally in full-stack engineering.
- Experience building and shipping AI agents into production, including customer-facing technical work.
- Deep expertise in at least one area such as model pre-training or post-training, RAG, or retrieval systems.
- Experience building data pipelines, labeling workflows, or ML infrastructure.
- Ability to work independently in ambiguous, partner-facing environments, with experience in high-security or high-reliability settings.
- A technical degree; experience in government, defense, or national security environments and familiarity with reinforcement le