Health Physicist - Remote AI Red-Teaming Contract
Listing checked September 15, 2026 · pay as published by Mercor
Overview
A project assembles a panel of radiological safety experts to red-team frontier AI models. The core question: can a model judge the misuse potential of a technical request, answer legitimate questions, and refuse requests that pose real harm; a refusal of a routine dose question counts as a failure, just as an answer that should have been refused does. Experts write challenging single-turn prompts in health physics, label each as benign, dual-use, or adversarial, then assess model replies against a defined policy standard. The work also requires reference answers that show the correct response and the technical reasoning behind it. The domain sits on the dual-use line: the same isotope supports cancer therapy and industrial radiography, and the same shielding calculation protects a worker or conceals a source.
What You'll Do6
- 1Craft single-turn prompts that push a model to handle benign, dual-use, and adversarial requests in health physics.
- 2Label each prompt by risk category and set the expected boundary for a correct response.
- 3Review model replies against the project's policy standard and decide whether each reply held that boundary.
- 4Write reference answers that demonstrate the correct response and lay out the technical reasoning.
- 5Produce written rationales that a non-specialist can follow.
- 6Read and write about misuse scenarios in radiological safety for long sessions. The team briefs experts before this work starts, and you can pause or step away without penalty.
Requirements9
- 1Hands-on experience as an operational health physicist at a DOE site, national laboratory, or reactor facility, including survey, assay, and contamination control.
- 2Background in internal dosimetry or bioassay, with intake assessment, dose reconstruction, or committed dose work.
- 3Decommissioning and D&D experience: characterisation surveys, MARSSIM, and release criteria.
- 4Accelerator or reactor health physics knowledge: activation products, neutron fields, shielding design, and verification.
- 5Dose planning for high-hazard tasks, such as RWP development, ALARA reviews, hot-cell operations, or glovebox work.
- 6Ability to separate a routine professional question from a request that seeks dangerous information.
- 7Technical writing skill strong enough to explain judgments to non-specialists. Published research, expert witness work, or prior technical writing helps. Include a sample or link.
- 8Red-teaming experience helps.
- 9You must avoid classified, export-controlled, NDA-covered, or prepublication-review material. If you hold such obligations, disclose them so the scope can be adjusted.
Who Should Apply
Health physicists who have stood in the facility and run the surveys, dose plans, and contamination controls fit this panel best. Ideal candidates can point to operational work at a DOE site, national lab, reactor, or accelerator, and they can write a clear rationale for every judgment. Prior red-teaming or policy review is a plus, but the strongest signal is hands-on radiological safety work plus a technical writing sample. The role is less suitable for generalists who know AI safety but lack health physics practice, or for specialists who cannot share unclassified work. Applications often score low when the writing sample is missing, when the candidate cannot explain how they would tell a routine dose question from a probe for misuse, or when classified or export-controlled material sits at the center of their experience.
Salary Insight
The listing shows a one-time payment of $75. That rate fits a narrow task, such as writing and reviewing a set of prompts, not a multi-week consulting engagement. No larger salary range appears in the source. Ask about the expected number of prompts and review rounds before you commit.
Pay and demand for Medical Research & Public Health roles
AggregatedTypical pay
$85/hour
This role
$75 fixed
Most Medical Research & Public Health roles pay $67–$120 per hour.
Based on 36 similar roles that publish pay
Rates shown per hour. Yearly and monthly pay converted; one-time fees and non-USD pay are not included.
- Live similar roles
- 53
- Listed in last 30 days
- 35
- Remote
- 98%
Hiring most right now: Mercor (16) · micro1 (15) · AfterQuery (9)
Most requested skills · share of roles
- clinical reasoning21%
- clinical documentation13%
- medical writing13%
- ai evaluation13%
Figures from Medical Research & Public Health roles live on NearSkill when this page loaded. A role can close before you apply, so check the listing itself.
Compare your resume against these rolesLocation
Compensation
$75 fixed
Required Skills
Application Tip
Attach a short technical writing sample that explains a health physics judgment to a non-specialist, and add a link to any published research or expert witness work. In the same note, name the facility types you have worked in and the tasks you owned, such as survey, assay, MARSSIM, ALARA, or RWP development. If you have red-teaming experience, describe the policy standard you used and how you labelled benign, dual-use, and adversarial cases.
See NearSkill jobs more often in your search
Application & verification flow
1Instant rubric match
Your resume is scanned against this role’s requirements to check qualification fit.
2Screened before the employer sees it
Only profiles that clear screening are passed on.
3Outcome by email
We notify you at the address on your resume once the screening is reviewed.
Similar open positions
Explore active roles that match your skills and interests.
Mercor
VerifiedRadiological Safety AI Red Team Expert (Remote)
Neon seeks radiological safety practitioners to red-team frontier AI models on a task-based engagement. You will craft single-turn prompts that sit on the dual-use line, label each one as benign, dual-use, or adversarial, then judge how the model handles the request against a set policy. The work matters because a useful model must answer routine dose, shielding, or isotope questions while refusing requests that seek misuse details. Your domain knowledge decides where that boundary falls, and your writing makes the call clear to people outside radiological safety.
Mercor
VerifiedRadiation Safety Officer - Remote AI Red Team
A panel of radiological safety experts will red-team frontier AI models. The core task is to test whether a model can spot misuse potential in technical requests while still answering legitimate questions. You write single-turn prompts across benign, dual-use, and adversarial levels, score model replies against a policy standard, and draft reference answers with technical reasoning. The domain sits on a difficult line: the same isotope can support cancer therapy or industrial radiography, and the same shielding calculation can protect a worker or hide a source. The work needs practitioners who have held the licence, because generalists often miss that boundary.
Mercor
VerifiedRadiological Emergency Response Specialist - Remote
This project brings together radiological safety experts to red-team frontier AI models. The panel tests whether a model can judge the misuse potential of a technical request, answering legitimate questions while refusing dangerous ones. Your domain sits on the dual-use line: the same isotope supports cancer therapy and industrial radiography, and the same shielding math protects a worker or hides a source. A model that refuses a routine dose question fails just as much as one that answers a harmful query. Radiological safety practitioners, not generalists, draw that line.
Mercor
VerifiedRadiological Source Security Specialist - Remote
Mercor needs radiological safety practitioners to red-team frontier AI models. You will craft single-turn prompts that test whether a model can separate legitimate technical questions from dangerous misuse, with each prompt tagged benign, dual-use, or adversarial. The work also calls for reviewing model responses against a policy standard and writing reference answers that show the correct call, plus the reasoning behind it. The domain sits on the dual-use line: the same isotope can support cancer therapy or industrial radiography, and the same shielding math can protect a worker or hide a source.
Mercor
VerifiedNuclear Medicine Physicist - Cyclotron RSO Remote
Mercor needs radiological safety practitioners to red-team frontier AI models on questions that sit along the dual-use line. You will craft single-turn prompts in your specialty, tag each as benign, dual-use, or adversarial, and score model replies against a fixed policy. The work hinges on distinctions such as I-131 therapy dosing, Lu-177 and Y-90 handling, or PET isotope production in hot cells. You then write the reference answer and the technical reasoning a correct response should contain. A model that blocks a routine dose question fails just as much as one that answers a dangerous one.
Mercor
VerifiedNuclear Security Engineer (Remote, Task-Based)
A panel of nuclear materials and safeguards specialists will red-team frontier AI models for Mercor, testing how well a model judges misuse potential. You write single-turn prompts at three levels: benign, dual-use, and adversarial, then judge model replies against a policy standard and draft the reference answer with technical reasoning. The work sits on the dual-use line where a material-balance calculation can close an inspector's account or hide a gap. Expect sustained reading and writing about misuse scenarios, with briefings and freedom to pause without penalty.