Chemicals Safety for Redteaming

• 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.

• Must have hands-on experience in synthesis, analytical chemistry, or chemical safety.
• Must be able to write challenging single-turn prompts in your domain, labelled across three levels: benign, dual-use, and adversarial.
• Must be able to evaluate the responses that come back against a defined policy standard, and judge whether each was handled correctly.
• Must be able to write the reference answer — what a correct response looks like, and the technical reasoning for why.
• Must have every judgment you make be written with a rationale that a non-specialist can follow.
• Work will not involve, and must not draw on, classified or export-controlled information, or anything covered by an NDA or prepublication review obligation.

• Prior AI evaluation or red-teaming experience is preferred.
• Prior technical writing, published research, or expert witness experience is a strong signal.
• Prior AI red-teaming or model evaluation experience is a plus but not required.

RequiredAlso useful

Project and contracting process: the hiring partner. Applications continue on the provider's website.