Nuclear Engineer — AI Red-Teaming & Safeguards

Mercor in New York is assembling a panel of nuclear domain experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous ones.

You will write challenging single-turn prompts in three levels: benign, dual-use, and adversarial. You will evaluate the responses against a defined policy standard and judge whether each was handled correctly.