LLM Engineer

Role overview Build and evaluate AI agents that carry out cyber-defense work in real customer environments. The role covers specialist agents, their coordination, and the controls that help them act safely, with human review for decisions that warrant it.

Responsibilities - Develop and assess agents for tasks such as discovery, exposure analysis, remediation, research, and reporting. - Build orchestration, reasoning workflows, tool use, and retrieval grounded in customer environments. - Own evaluation methods and use measured results to determine whether systems are ready to ship. - Set appropriate limits on autonomous actions and include human approval where the consequences require it. - Apply new model capabilities to product quickly while maintaining reliability and safety.

Requirements - Production experience building with large language models, including agents, tool use, retrieval-augmented generation, and evaluations. - Strong Python skills and practical understanding of how modern models behave, fail, and can be guided. - Experience shipping an AI system where errors had meaningful consequences. - Ability to build guardrails and evaluations that demonstrate system performance. - A rigorous, measurement-focused approach to ambiguous problems.