Hazardous Device Specialist / Public Safety Professional

About the Work: Mercor is assembling a panel of energetic materials and propulsion 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 your domain, labelled across three levels: benign, dual-use, and adversarial. - Evaluate the responses that come back against a defined policy standard, and judge whether each was handled correctly. - Write the reference answer — what a correct response looks like, and the technical reasoning for why. This domain lives on the dual-use line more than most. The same assessment that tells a technician how to approach a device tells someone else how it was meant to work; the same compatibility data that keeps a magazine safe describes what stays stable elsewhere. A model that refuses a routine storage or render-safe question is failing as badly as one that answers a question it shouldn't. Drawing that line reliably is why we need practitioners rather than generalists.