Frontier AI Safety Evaluator
Listed on 2026-09-25
-
IT/Tech
AI Evaluation, Data Annotation/ AI Labeling
Obsidian is seeking experienced AI Safety Practitioners to evaluate the safety, quality, and alignment of frontier AI models across complex, policy-sensitive topics. You will assess AI-generated responses, apply safety policies, and provide structured feedback to improve model behavior through evaluations and collaboration with AI researchers and safety teams.
Responsibilities include iterating on rubrics for RLHF, SFT, and safety benchmarking, identifying unsafe outputs and misalignment, and
For the Frontier AI Safety Evaluator position at Obsidian, we are reviewing applications now.
We are looking to fill the Frontier AI Safety Evaluator position at Obsidian in San Francisco, CA, United States.
The Frontier AI Safety Evaluator role at Obsidian is now open for applications in San Francisco, CA, United States.
Join us at Obsidian as our next Frontier AI Safety Evaluator in San Francisco, CA, United States.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).