Analytical Chemist

Mercor is assembling a panel of chemistry and chemical safety experts to red-team frontier AI models, testing whether a model correctly judges the misuse potential of technical requests: answering legitimate questions fully while refusing dangerous ones. Remote contract, paid $65–$75 per task.

You will:

• Write challenging single-turn prompts in your domain, labelled benign, dual-use or adversarial
• Evaluate model responses against a defined policy standard
• Write the reference answer and the technical reasoning behind it

Relevant backgrounds (ideally with red-teaming experience):

• Detection and identification of hazardous compounds (GC-MS, LC-MS/MS, IR, NMR)
• Method development and validation for trace-level analysis
• Environmental, occupational or emergency-response sampling and analysis
• Reference standards, spectral libraries and unknown identification
• Laboratory accreditation, QA/QC and proficiency testing

This is writing-intensive work: every judgment needs a written rationale a non-specialist can follow. Technical writing, published research or expert witness experience is a strong signal. You will read and write about misuse scenarios for sustained periods and can pause at any time. The work must not draw on classified, export-controlled or NDA-covered information.