Toxicological Chemist - Fully Remote | Upto $75/task Task based

Obsidian; New York (NY); Remote; USD 90,000 - 120,000; Full time

Job summary

Mercor is assembling a panel of chemistry and chemical safety experts to red-team frontier AI models, testing whether a model can judge misuse potential while answering legitimate questions fully and refusing dangerous ones.

You will craft prompts, evaluate responses, and write the reference answer with detailed technical reasoning to support policy standards.

Qualifications

• We look for people who have done casework—identifying substances and precursors, and defending the conclusion in a report or on the stand.
• Ability to tell routine professional questions from lines that may be fishing for something else; this is critical in mis-use scenario work.
• Prior technical writing, published research, or expert witness experience is a strong signal.

Responsibilities

• Write challenging single-turn prompts in domains: benign, dual-use, and adversarial.
• Evaluate model responses against a policy standard and judge handling correctness.
• Write the reference answer and technical reasoning detailing why it is correct.

Skills

Casework experience

Red-teaming

Forensic chemistry

Expert testimony

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 casework knowledge that identifies a substance describes how it was produced; the same precursor list that supports an investigation is a shopping list read backwards. A model that refuses a routine identification or casework 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 done casework — identifying substances and precursors, and defending the conclusion in a report or on the stand. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same precursor knowledge that identifies a clandestine route is the route. 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):

• Controlled substance casework in a forensic laboratory — identification and quantitation
• Clandestine laboratory response, precursor identification and scene chemistry
• Forensic toxicology — postmortem or human performance casework
• Seized-drug and precursor trend monitoring or intelligence analysis
• Expert testimony and report writing on chemical casework

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.