Frontier AI Safety Red Team Expert
Listed on 2026-10-20
-
Science
AI Evaluation, Data Annotation/ AI Labeling
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.
We have an opening for a Frontier AI Safety Red Team Expert in New York, NY, United States within IT & Technology, Other.
The following opening is for a Frontier AI Safety Red Team Expert with Mercor.
Our team is growing, and we are hiring a Frontier AI Safety Red Team Expert in New York, NY, United States.
This opening is for the Frontier AI Safety Red Team Expert role at Mercor.
(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).