Frontier AI Safety Evaluator & Model Alignment Expert

Obsidian is seeking experienced AI Safety Practitioners to evaluate frontier AI models across complex, policy-sensitive, and ambiguous thoughts. You will assess AI-generated responses, apply safety policies, and help improve model behavior through structured evaluations and feedback.

Responsibilities include evaluating safety, factual accuracy, and policy compliance; reviewing content on misinformation, political persuasion, self-harm, violence, cyber, and biosecurity; applying evaluation