Frontier AI Safety Red Team Expert
Listed on 2026-10-02
-
IT/Tech
AI Evaluation, Information Security & Data Protection, Cybersecurity, AI Business & Operations
Obsidian is seeking experienced AI Safety Red Teamers to stress-test frontier AI models through adversarial testing and prompt design. You will identify jailbreaks, unsafe behaviours, and policy failures while evaluating model behavior across sensitive domains.
Collaborating with AI researchers, you will contribute to safety benchmarking, vulnerability documentation, and research to improve alignment and robustness of frontier AI systems.
For the Frontier AI Safety Red Team Expert position at Obsidian, we are reviewing applications now.
Learn more about the Frontier AI Safety Red Team Expert role in the description above.
We appreciate your interest in this position.
Join Obsidian and contribute to our ongoing work.
Take a moment to read everything above and see whether this role is right for you.
This posting is for the Frontier AI Safety Red Team Expert role at Obsidian, based in New York, NY, 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).