Radiological Source Security Specialist - Remote
Listing checked September 15, 2026 · pay as published by Mercor
Overview
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.
What You'll Do6
- 1Write single-turn prompts from your radiological security background and label each one benign, dual-use, or adversarial.
- 2Test model outputs against the stated policy standard and decide if each response handled the request in the right way.
- 3Draft the reference answer for every prompt, including the technical basis for the judgment.
- 4Explain your calls in plain language so a reader without radiological training can follow the reasoning.
- 5Review misuse scenarios in your specialty across long writing sessions, with breaks allowed when needed.
- 6Flag any prompt or response that touches on information you cannot discuss due to NDA, export control, or prepublication review.
Requirements9
- 1Hands-on work assessing how Category 1 and 2 sources can be stolen, shielded, or moved within a licensed programme.
- 2Ability to separate a routine professional question from one that seeks harmful operational detail.
- 3Experience with physical protection design or review, including detect, delay, assess, and respond tactics and insider threat factors.
- 4Background in source recovery, consolidation, or security upgrades for disused and orphan sources.
- 5Knowledge of regulatory security inspection and compliance, such as 10 CFR 37 or a national equivalent.
- 6Familiarity with transport security for radioactive material, covering routing, escort, tracking, and chain of custody.
- 7Strong technical writing, published research, or expert witness work, with a sample or link ready.
- 8Red-teaming experience is a plus, including work against AI models or in security vulnerability assessments.
- 9No reliance on classified, export-controlled, NDA-covered, or prepublication-review material; disclose any such obligations.
Who Should Apply
Ideal candidates have assessed real Category 1 and 2 source security, not just filled out compliance paperwork. You can read a technical request, spot when it crosses from training or safety into theft, shielding, or movement planning, and defend that call in writing. A background in physical protection, source recovery, transport security, or 10 CFR 37 inspections fits well, and prior red-teaming or model evaluation helps. This role suits specialists who enjoy sustained writing about misuse scenarios; it is less suitable for generalists, policy-only reviewers, or anyone who cannot share a writing sample. Applications often score low when the candidate lists broad regulatory knowledge without concrete source security work, or when they skip the required writing sample and rationale example.
Salary Insight
The listing offers a one-time payment of $75. That amount covers a single task, so it is not an hourly or annual salary; treat it as project-based compensation for the prompt set and evaluations you complete.
Pay and demand for Cybersecurity roles
AggregatedTypical pay
$55/hour
This role
$75 fixed
Most Cybersecurity roles pay $35–$78 per hour.
Based on 44 similar roles that publish pay · 3 publish only a top rate; those count at the rate they gave
Rates shown per hour. Yearly and monthly pay converted; one-time fees and non-USD pay are not included.
- Live similar roles
- 58
- Listed in last 30 days
- 27
- Remote
- 97%
Hiring most right now: Neon (27) · micro1 (16) · AfterQuery (4)
Most requested skills · share of roles
- red teaming34%
- penetration testing29%
- reverse engineering28%
- technical writing28%
Figures from Cybersecurity 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
Send a short writing sample that shows how you explain a dual-use judgment to a non-specialist, then add one concrete example from Category 1 or 2 source security, such as a physical protection review or transport chain-of-custody assessment. State any NDA, export-control, or prepublication obligations in your application so the team can scope the task.
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
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
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
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.
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
VerifiedHealth Physicist - Remote AI Red-Teaming Contract
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.