Jobs

Aslan is seeking its first Evals Lead to ensure the quality and effectiveness of its autonomous agents, which operate for weeks across external systems. This critical role involves daily platform operation, building robust evaluation tooling, and owning the decision to ship in an environment where fixes cannot be pushed post-delivery. The ideal candidate has experience owning evaluations for LLM or agent products, building labeled datasets for training, and a strong background in Python and production-grade evals frameworks. You will define regressions, diagnose agent decision-making, and build simulation harnesses to validate agent performance.