Open-Model AI Safety Lead: Red Team & Validation | Equity

A cutting-edge AI company in Greater London is seeking an individual with a graduate degree in Computer Science or related fields to lead the red-teaming and adversarial evaluation of their models. The role requires a deep understanding of LLM safety, strong software engineering skills, and experience with Reinforcement Learning. Ideal candidates thrive in a dynamic environment and are passionate about AI advancements. This position offers competitive compensation and comprehensive health benefits.