Mercor is assembling a panel of nuclear domain experts in Greater London to red-team frontier AI models. The aim is to test whether a model can correctly judge misuse potential by answering legitimate questions fully while refusing dangerous ones.
You will write prompts across benign, dual-use, and adversarial categories, evaluate model responses, and draft the reference answer with technical reasoning. This is a writing-intensive, policy-focused role requiring clear rationale for every judgment.
#J-18808-Ljbffr
Nuclear AI Safety Red-Teaming Engineer 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.
