Chemical Defense Researcher
Posted on September 14, 2026 · Applications until October 18, 2026
I am sending you to the official Mercor page. Applying is free and in English.
I earn a commission from the platform when a candidate I referred gets hired. It changes nothing for you.
The Chemical Defense Researcher writes prompts and evaluates frontier AI models for chemical safety and misuse potential. Candidates need a strong institutional background in chemical defense, countermeasures, or toxicology, along with proven technical writing skills.
Description in English, as published by Mercor.
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 toxicology that sets a countermeasure dose describes an exposure someone might intend; the same decontamination data that protects responders tells you what defeats it. A model that refuses a routine countermeasure or PPE 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 worked chemical threats from the defensive side in an institutional setting, countermeasures, protection, detection, verification. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same agent properties that drive a treatment protocol drive a threat assessment. 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):
- Chemical defence research at USAMRICD, DoD, CDC or an allied national institute
- Toxicology of chemical warfare agents and medical countermeasure development
- Decontamination, protection and detection research for chemical threats
- CWC-related work, verification, destruction, designated laboratory analysis
- Consequence assessment and medical management of chemical exposure
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.
About Mercor
Mercor is a US marketplace hiring remote experts for AI and consulting projects, from law to engineering. The original posting is on their site.
View this job on MercorMore jobs in Sciences and research
Subject Matter Expert, Data & Statistical Chart Analysis
This remote contractor position involves interpreting complex data visualizations and designing objective analytical tasks to train advanced AI models. Candidates need a quantitative degree or equivalent experience, alongside at least two years of professional background working with statistical models.
- Chart interpretation accuracy
- Multi-step quantitative reasoning
- Question design / unambiguous task construction
- +2
Posted yesterday$25 to $50/h
Subject Matter Expert, Medicine & Biostatistics Chart Analysis
The Subject Matter Expert interprets complex medical and biostatistical charts to design reasoning tasks for advanced AI models. Candidates need a degree in medicine, biostatistics, or a related field, plus two years of experience analyzing clinical trial data.
- Chart interpretation accuracy
- Multi-step quantitative reasoning
- Question design / unambiguous task construction
- +2
Posted yesterday$25 to $50/h
Apple Watch Users: Opportunity for You
The contributor populates their Apple HealthKit profile with comprehensive health data and links electronic health records from a specified qualifying medical institution. Key requirements include providing continuous history, clinical notes, and four basic demographic attributes.
Posted 2 days ago
Get paid to support Wellness Research (US Only)
Contribute de-identified Apple Health and clinical records data to wellness research datasets. Requirements include linking a qualifying health provider and providing full profile data with clinical notes.
Posted 2 days ago