Mercor is seeking experienced AI Safety Practitioners to evaluate frontier AI models across complex, policy-sensitive topics, ensuring safety, quality, and alignment. You will assess AI-generated responses, apply safety policies, and help improve model behavior through structured evaluations and feedback, collaborating with product teams and researchers.
Responsibilities include refining RLHF/SFT rubrics, identifying unsafe outputs, hallucinations, and policy violations; providing actionable
#J-18808-LjbffrFrontier AI Safety Evaluator & Policy Expert in san francisco at Unknown Company
This position is listed as full time and onsite.