Energetic Materials Red Teaming Expert (Remote)
Listing checked September 15, 2026 · pay as published by Mercor
Overview
The panel tests frontier AI models on how they handle explosive and energetic materials requests. You write single-turn prompts split into benign, dual-use, and adversarial levels, then judge model replies against a fixed policy. Your reference answers show what a sound response looks like and explain the technical reasoning behind that call. The work matters because models both refuse routine mining or investigation questions and answer dangerous requests dressed as academic work. Energetic materials, red teaming, and AI evaluation sit at the center of the task.
What You'll Do7
- 1Draft single-turn prompts that cover benign, dual-use, and adversarial cases in your specialty.
- 2Label each prompt with the correct risk level and the policy category it tests.
- 3Review model responses against the project policy standard and decide if the model handled the request well.
- 4Write reference answers that demonstrate a sound response and the technical basis for it.
- 5Explain your reasoning in plain language that non-specialists on the panel can follow.
- 6Flag failure patterns where a model over-refuses normal professional questions or under-refuses harmful ones.
- 7Submit prompt, response, and rationale as a complete task package.
Requirements7
- 1Deep domain knowledge in one or more areas: pyrotechnics, propulsion, initiation systems, hazardous device render-safe work, forensic materials identification, or commercial blasting.
- 2Experience as a specialty materials chemist, propulsion and effects engineer, hazardous device specialist, federal materials analyst, or blasting engineer.
- 3Ability to write technical rationale that a non-specialist can follow.
- 4Prior technical writing, incident reports, post-blast reports, published research, or expert witness work. Include a sample or link.
- 5AI evaluation or red-teaming experience preferred.
- 6Comfort with reading and writing about misuse scenarios in your field for sustained periods.
- 7No use of classified, export-controlled, NDA-covered, or prepublication-review material. Disclose any such obligations so the team can scope the task.
Who Should Apply
Ideal candidates have hands-on depth in energetic materials, whether from pyrotechnics formulation, propulsion design, render-safe procedures, forensic scene work, or commercial blasting. They can separate a routine mining or investigation question from an adversarial request, then write a clear rationale for that call. The role suits people with reporting or research writing habits, because every judgment needs a written defense. Candidates who lack direct energetic materials experience, or who cannot provide a writing sample, tend to score low. A common rejection reason is treating all technical questions as dangerous; another is failing to show how you have handled real misuse scenarios or policy judgments in your field.
Salary Insight
The source lists a one-time $75 fee for task-based work. This is a fixed micro-task payment rather than a salary or hourly rate. Treat the $75 as compensation for one completed expert task, and confirm the expected scope with the team.
Location
Compensation
$75 fixed
Required Skills
Application Tip
Attach a redacted writing sample or link that shows you explaining a technical judgment to a non-specialist, such as an incident report, post-blast report, published study, or expert witness statement. In your application, name your specialty (pyrotechnics, propulsion, render-safe, forensic ID, or blasting) and state any NDA, export-control, or prepublication limits so the team can scope the task. Mention any prior AI evaluation or red-teaming work, even if it was small.
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
VerifiedFederal Materials Specialist - Incident Analyst
A panel of energetic materials and propulsion experts will red-team frontier AI models. The goal: test whether a model can judge misuse potential in a technical request, answering legitimate questions while refusing dangerous ones. You will write single-turn prompts labeled benign, dual-use, and adversarial, then evaluate model responses against a policy standard. For each prompt, you also write the reference answer and the technical reasoning behind it. The domain sits on the dual-use line, where routine residue analysis can look like a recipe in reverse.
Mercor
VerifiedPropulsion & Effects Engineer - Remote AI Red Teaming
This task-based remote project brings together propulsion and energetic materials specialists to red-team frontier AI models. The panel tests whether a model can judge the misuse potential of a technical request: answering legitimate questions and refusing dangerous ones. You will write single-turn prompts across three labels, benign, dual-use, and adversarial, then review model responses against a policy standard. The domain sits on the dual-use line, where the same analysis that qualifies a motor for flight also describes a capability. This work needs practitioners because generalists struggle to draw that line with consistency.
Mercor
VerifiedChemistry AI Red-Teaming Expert (Remote)
Neon seeks chemistry domain experts to red-team frontier AI models. The core test asks whether a model can separate a safe technical question from a harmful one. You will design single-turn prompts tagged benign, dual-use, or adversarial, then check how the model answers against a policy standard. The job hinges on calibration. A harmless prompt that the model rejects matters as much as a harmful prompt it approves.
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
VerifiedAnalytical Chemist - Remote AI Red-Teaming
Chemistry and chemical safety specialists will join a red-team panel that probes how well frontier AI models handle misuse risk. The task centers on single-turn prompts written at three labels: benign, dual-use, and adversarial, and on judging each prompt against a policy standard. You also draft reference answers that show the correct response and explain the technical reasoning. Relevant method areas include GC-MS, LC-MS/MS, IR, and NMR, plus trace-level validation and unknown identification.
Mercor
VerifiedSpecialty Materials Chemist - Pyrotechnics/Propulsion
Neon seeks chemists who have formulated, synthesized, and tested energetic materials in licensed or government labs. The work supports a red-team panel that checks whether frontier AI models can separate a routine technical request from a dangerous one. You will write prompts that sit on the benign, dual-use, and adversarial lines, then judge model responses against a policy standard. Expect a writing-heavy task with room to pause, and a strict rule against using classified or export-controlled data.