About Mercor: Health PhysicistCompany: MercorCompensation: $65-$75 per taskCommitment: ContractLocation: RemoteReferral Reward: Earn up to $250 per successful referral.Referral Link: https://t.mercor.com/N2UM5About the work
Mercor is assembling a panel of radiological 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 isotope underpins cancer therapy and industrial radiography; the same shielding calculation protects a worker and conceals a source. A model that refuses a routine dose 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 the measurement and the dose planning themselves, in a facility where getting it wrong mattered — survey, assay, contamination control, work planning. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same shielding calculation protects a worker and conceals a source. 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):
Operational health physicist at a DOE site, national laboratory or reactor facility — survey, assay, contamination control
Internal dosimetry or bioassay specialist — intake assessment, dose reconstruction, committed dose
Decommissioning and D&D health physicist — characterisation surveys, MARSSIM, release criteria
Accelerator or reactor health physics — activation products, neutron fields, shielding design and verification
Dose planning for high-hazard work — RWP development, ALARA reviews, hot-cell and glovebox operations
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.
We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.
About Mercor: Source Security SpecialistCompany: MercorCompensation: $65-$75 per taskCommitment: ContractLocation: RemoteReferral Reward: Earn up to $250 per successful referral.Referral Link: https://t.mercor.com/6lpwpAbout the work
Mercor is assembling a panel of radiological 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 isotope underpins cancer therapy and industrial radiography; the same shielding calculation protects a worker and conceals a source. A model that refuses a routine dose 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 how Category 1 and 2 sources actually get stolen, shielded or moved — the security and vulnerability side of a licensed programme, not just its paperwork. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same shielding calculation protects a worker and conceals a source. 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):
Security or vulnerability assessment of licensed facilities holding Category 1 and 2 sources
Physical protection design and review — detect, delay, assess and respond; insider threat considerations
Source recovery, consolidation or security-upgrade programmes for disused and orphan sources
Regulatory security inspection and compliance — 10 CFR 37 or national equivalents
Transport security for radioactive material — routing, escort, tracking and chain of custody
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.
We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.
About Mercor: Emergency Response SpecialistCompany: MercorCompensation: $65-$75 per taskCommitment: ContractLocation: RemoteReferral Reward: Earn up to $250 per successful referral.Referral Link: https://t.mercor.com/Fv7HoAbout the work
Mercor is assembling a panel of radiological 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 isotope underpins cancer therapy and industrial radiography; the same shielding calculation protects a worker and conceals a source. A model that refuses a routine dose 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 planned for or responded to a radiological event — the consequence, contamination and protective-action side, held as a real responsibility rather than a tabletop interest. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same dispersal model that drives an evacuation decision also describes an effect someone might want. 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):
Radiological emergency planning at a licensed facility, or at state or national level — plans, drills, exercises
Field response and monitoring — FRMAC, RAP, CBRN or national radiological response teams
Consequence and dispersal modelling — plume and deposition estimates, dose projection, protective action decisions
Incident command or response coordination for a radiological event or full-scale exercise
Medical and public-health radiological response — triage, countermeasures, population monitoring
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.
We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.
About Mercor: Nuclear Medicine Physicist / Cyclotron RSOCompany: MercorCompensation: $65-$75 per taskCommitment: ContractLocation: RemoteReferral Reward: Earn up to $250 per successful referral.Referral Link: https://t.mercor.com/yOiDQAbout the work
Mercor is assembling a panel of radiological 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 isotope underpins cancer therapy and industrial radiography; the same shielding calculation protects a worker and conceals a source. A model that refuses a routine dose 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 produce and handle medical isotopes — the legitimate-use half of the dual-use line, held as a real custody responsibility. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same activity and shielding figures that let a patient go home describe a source someone else wants to move quietly. 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):
Nuclear medicine or radiopharmacy physicist — therapy dosimetry, I-131, Lu-177 and Y-90 work, patient release criteria
Cyclotron or radiochemistry facility RSO — target handling, PET isotope production, hot-cell operations
Medical physicist with brachytherapy source custody — HDR and LDR sources, inventory and source exchange
Radiopharmaceutical production and QC under GMP or an equivalent quality system
Authorised Medical Physicist or Authorised User support on a medical radioactive materials licence
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.
We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.
About Mercor: Nuclear Engineer, Fuel CycleCompany: MercorCompensation: $65-$75 per taskCommitment: ContractLocation: RemoteReferral Reward: Earn up to $250 per successful referral.Referral Link: https://t.mercor.com/jWerhAbout the work
Mercor is assembling a panel of nuclear materials and safeguards 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 material-balance calculation that closes an inspector's account can be used to hide what is missing from it; the same fuel-cycle step that supplies a power reactor is the one a proliferation pathway runs through. A model that refuses a routine criticality-safety 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 the fuel cycle itself — enrichment, reprocessing, fabrication, criticality safety — and who know which parameters are routine engineering and which ones only matter to someone going somewhere else with them. What matters most is being able to tell a routine professional question from one that's fishing for something else. 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):
Enrichment, conversion or fuel fabrication engineering — process design, operations, throughput
Reprocessing and back-end fuel cycle — separations, waste streams, spent fuel management
Criticality safety engineer — criticality safety evaluations, limits and controls, accident analysis
Fuel cycle systems analysis and modelling — material flows, cycle performance and economics
Safety analysis or licensing for a fuel-cycle facility
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.
We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.
