Industrial Hygienist - Safety Expert

Mercor; San Francisco (CA); On-site; USD 120,000 - 180,000; 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 the responses against a defined policy standard, and craft reference answers with the technical reasoning behind them.

Qualifications

• Background in real exposures and process hazards.
• Experience signing off on controls and risk assessments.
• Ability to distinguish routine professional questions from misuse./risks.

Responsibilities

• Write prompts across benign, dual-use, and adversarial levels.
• Evaluate model responses against a policy standard.
• Draft reference answers with technical rationale.

Skills

Industrial hygiene

HAZOP

LOPA

What-if studies

Toxic release modelling

Education

Certified industrial hygienist

PSM/COMAH/OSHA knowledge

Tools

Regulatory frameworks

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.