Industrial Hygienist - Safety Expert - AI Trainer

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. You will craft prompts across benign, dual-use, and adversarial categories and document the rationale for each choice.

This role emphasizes precise technical writing and careful judgment. You will evaluate model responses against a policy standard and produce a reference answer with reasoning to align AI behavior with safety norms.

Qualifications

• Experience in red‑teaming and risk assessment for process safety.
• Strong technical writing with ability to justify conclusions clearly.
• Ability to distinguish routine questions from high-risk misuse scenarios.

Responsibilities

• Write challenging prompts across benign, dual-use, and adversarial categories.
• Evaluate model responses against a defined policy standard.
• Produce a reference answer with technical reasoning for safe use.

Skills

Red-teaming experience

Technical writing

Critical thinking

Hazard assessment

Education

Certified industrial hygienist

HAZOP/LOPA training

Tools

HAZOP

LOPA

Toxic release modelling

PPE program design

Job description

About the work

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 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.

This domain lives on the dual-use line more than most. The same dispersion model that sites a plant and sets an evacuation radius also predicts an exposure; the same hazard analysis that finds a failure path is a list of failure paths. A model that refuses a routine exposure-limit question is failing as badly as one that answers a question it shouldn't. Drawing that line reliably is why we need practitioners rather than generalists.

Background we're looking for

We're looking for people who have assessed real exposures and real process hazards, and signed off on the controls. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same release model that protects a community estimates a consequence. You will be writing prompts that sit exactly on that line, then judging whether the model held it.

Examples of relevant backgrounds (ideally with red-teaming experience):

• Certified industrial hygienist — exposure assessment, sampling strategy, control banding
• Process hazard analysis — HAZOP, LOPA, what-if studies, management of change
• Toxic release and dispersion modelling — consequence analysis, AEGL/ERPG criteria, facility siting
• Ventilation, containment and PPE programme design for chemical hazards
• Regulatory compliance — PSM, Seveso, COMAH, OSHA or national equivalents

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. You will also be reading and writing about misuse scenarios in your field for sustained periods. We brief experts on this in advance, and you can pause or step away at any point without penalty.

Before you apply

Your work here will not involve, and must not draw on, classified or export-controlled information, or anything covered by an NDA or prepublication review obligation. If you hold such obligations you may still be a good fit; tell us in your application and we will scope the work accordingly.