Mercor is assembling a panel of nuclear materials and safeguards experts to red‑team frontier AI models to test misuse potential while ensuring safe, robust responses. You will write prompts across benign, dual‑use, and adversarial levels and judge model outputs against a defined policy standard, then draft reference answers with clear technical reasoning.
This writing‑intensive role focuses on distinguishing routine professional questions from probing or sensitive inquiries.
#J-18808-Ljbffr
Nuclear Safeguards Red Team Specialist in London employer: Mercor
Mercor is an exceptional employer that champions innovation and creativity in the AI sector, offering a fully remote work environment that promotes flexibility and independence. With a strong focus on employee growth, team members are encouraged to take ownership of their projects while benefiting from a supportive culture that values collaboration and continuous learning. Joining Mercor means being part of a forward-thinking company backed by industry leaders, where your contributions directly impact cutting-edge search technologies.
