Chemist for AI Safety Red Team & Hazard Analysis

Mercor; New York (NY); On-site; USD 90,000 - 130,000; Full time

Job summary

Mercor is assembling a panel of chemistry and chemical safety 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 prompts across benign, dual-use, and adversarial levels, evaluate model responses against a policy standard, and draft the reference answers with the technical reasoning.

Qualifications

• Experience in hazardous compounds detection and identification.
• Ability to develop and validate trace-level analysis methods.
• Experience with environmental or emergency-response sampling.

Responsibilities

• Create challenging single-turn prompts across benign, dual-use, and adversarial categories.
• Evaluate model responses against a policy standard and document judgments.
• Draft reference answers and technical rationales for misuse screening.

Skills

Hazardous compounds detection & ID

Red-team / adversarial analysis

Technical writing

Spectral analysis tools

Tools

GC-MS

LC-MS/MS

IR

NMR

Job description

Mercor is assembling a panel of chemistry and chemical safety 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 prompts across benign, dual-use, and adversarial levels, evaluate model responses against a policy standard, and draft the reference answers with the technical reasoning.