Mercor
Chemicals Safety for Redteaming
- Pay
- $65–75/task
- Type
- Task-based
- Location
- Remote
- Posted
- Sep 9, 2026
Tip: In our experience, people who apply through a referral link have a better chance of being selected, as I’m also working on Mercor.
Free to apply. Our referral link costs you nothing and doesn’t change your pay. If you’re hired, Mercor may pay us a bonus, which keeps this site free. Never pay anyone to get AI training work.
About this role
About the work Mercor is assembling a panel of chemistry 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 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. The hard part is calibration, not difficulty. A benign prompt that a model wrongly refuses is as valuable as an adversarial one it wrongly answers. That judgment is why we need domain experts rather than generalists — in chemistry the line sits between mechanism and…
