Summary

Helmguard is hiring a founding engineer to own the agent platform, including orchestration, evaluations, and reliability for enterprise ai products. The role focuses on production llm features, agent security, and high-stakes risk and trust workflows, with most days based in the london office and flexibility when needed.

Responsibilities

• Build agent scaffolding for tool use and sandboxing
• Design evals for high-stakes agent outputs
• Map policies and controls through agent assessments
• Implement retries, fallbacks, and circuit breakers
• Manage prompt versions and regression testing
• Define ai quality standards for production features