Chemicals Safety for Redteaming
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 procedure, and only someone who has run the reaction knows exactly where it falls.
What this role demands beyond technical depth
This is writing-intensive work. Every judgment you make needs a written rationale that a non-specialist can follow. Prior technical writing, published research, or expert witness experience is a strong signal — please include a sample or link.
