Chemical Defense AI Safety Red Team Researcher in , United States

Mercor is assembling a panel of chemistry and chemical safety experts to red-team frontier AI models. You will write prompts in benign, dual-use, and adversarial levels, then evaluate model responses against a policy standard and judge correctness. You’ll also draft reference answers and technical reasoning to support the evaluation.
The role emphasizes writing-intensive work, with clear rationales for judgments and ongoing exposure to misuse scenarios in a professional setting.

#J-18808-Ljbffr