Explosives & Energetic Materials Expert for AI Safety Audit
What you'll do
This is a safety-evaluation role. Each task gives you a user request and the answers three different AI models gave. You classify the request as benign, dual-use or adversarial, mark each answer safe or unsafe and explain why, rank the three, and write the answer the model should have given. For dual-use requests you also note what makes the request sensitive, what legitimate purpose it serves and who should be able to get an answer.
The ad stresses that the requests are realistic, coming from blasting engineers, pyrotechnicians, propellant chemists, bomb technicians and investigators as well as the occasional bad actor, and that catching ordinary professional questions that models wrongly refuse matters as much as catching dangerous ones. The skill being bought is judgement about specificity: what stays at a safe, educational level and what would enable unsafe handling or misuse.
Who fits
The ad names commercial blasting and mining explosives specialists, military or police EOD and bomb technicians, energetic materials, propellant and pyrotechnics chemists, post-blast investigators and forensic examiners, and explosives safety officers or regulators.
- A degree in chemistry, chemical or materials engineering, explosives engineering, safety engineering, hazmat management, EHS or a close field, or professional safety certification
- 3+ years in explosives safety, energetic materials, hazardous materials or industrial safety (the description says five or more is usual)
- Familiarity with Safety Data Sheets, GHS and risk-assessment frameworks
- Excellent written English for structured explanations
AI safety, red-team, content moderation or rubric-based evaluation experience is preferred. Open only to citizens or permanent residents of the US, UK, Canada, Australia, New Zealand and the European Union; the listing covers 32 countries.
What it pays
The ad lists $1 to $100 an hour. A $1 floor is almost certainly a placeholder for an unspecified lower bound, and the ad does not say how the rate is set, so confirm it at offer stage. The board tags the engagement as full time even though pay is hourly. The ad does not describe payment terms; SuperAnnotate's company page covers the Deel contract, paid bootcamp and monitoring software that apply across its hourly projects.
Worth knowing
Good:
- Specialist expertise in a field where few reviewers qualify
- Judgement work, including pushing back on needless refusals, not just blocking content
- A high stated ceiling
Less good:
- The $1 to $100 range is very wide and unexplained
- Sensitive subject matter, and the ad does not describe any support around exposure to it
- The full-time tag is unclear against hourly pay, with no hours published
- Residency limited to citizens or permanent residents of the listed regions
About this listing
Read from the SME Careers jobs board on 27 October 2026; no posting date is shown. Pay, countries and requirements are the ad's own. This page describes the role only and contains no technical detail on the subject matter. See SuperAnnotate.
Before the interview: SuperAnnotate interview guides
More roles at SuperAnnotate
See all 261Similar roles at other platforms
- AI Coding Response Review (Expert)Invisible Technologies · $25 / Hour · 1d ago
- Subject-Matter AI Evaluation Contributor: Independent ContractorInvisible Technologies · $21 / Hour · 1d ago
- AI Agent Tester: Real-World Tasksmicro1 · $25 – $45 / Hour · 5d ago
- Radiology Residents: Medical Image Evaluation for AI Benchmarks ($90/hr)Terac · $90 / Hour · 7d ago
Guides about SuperAnnotate
Browse similar roles
Not the right fit?
See every open role, or get new ones on Telegram or Discord as they are added.