Energetic Materials Expert for Redteaming

About the Work: Mercor is assembling a panel of explosives and energetic materials 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. Models tend to fail this domain in both directions: refusing routine questions a mining engineer or investigator asks daily, then engaging with a request they should have shut down because it arrived in academic clothing. Knowing which is which takes someone who has done the work.