Mercor seeks specialists to join a panel testing frontier AI models for misuse potential in nuclear-safeguards contexts. You will craft prompts across benign, dual-use, and adversarial levels and assess model outputs against policy standards.
Applicants should bring experience in export controls, treaty implementation, or proliferation analysis, and be prepared to document judgments with clear rationales.
#J-18808-LjbffrNuclear Safeguards Red-Teaming Specialist in new york at Unknown Company
This position is listed as full time and onsite.