AI Safety Chemist — Hazardous Chemistry Red-Teaming

Mercor; San Francisco (CA); Remote; USD 120,000 - 190,000; Full time

Job summary

Mercor is assembling a panel of chemistry and chemical safety experts to red-team frontier AI models. You will write challenging prompts at three levels (benign, dual-use, adversarial) and evaluate model responses against a defined policy standard, providing a reference answer with technical reasoning.

This writing-intensive role requires the ability to articulate clear judgments about misuse scenarios in your field, and to share a rationale accessible to non-specialists.

Qualifications

• Background in detection and identification of hazardous compounds (e.g., GC-MS, LC-MS/MS, IR, NMR).
• Experience with method development and validation for trace-level analysis.
• Experience in environmental, occupational, or emergency-response sampling and analysis.
• Working with reference standards, spectral libraries and unknown identification.
• Experience with laboratory accreditation, QA/QC and proficiency testing.

Responsibilities

• Write challenging single-turn prompts across three levels: benign, dual-use, and adversarial.
• Evaluate model responses against a defined policy standard and judge correctness.
• Write the reference answer and technical reasoning for why a response is correct.

Skills

Hazardous compounds knowledge

Red-teaming / adversarial thinking

Technical writing

Detection limits understanding

Job description

Mercor is assembling a panel of chemistry and chemical safety experts to red-team frontier AI models. You will write challenging prompts at three levels (benign, dual-use, adversarial) and evaluate model responses against a defined policy standard, providing a reference answer with technical reasoning.

This writing-intensive role requires the ability to articulate clear judgments about misuse scenarios in your field, and to share a rationale accessible to non-specialists.