Each task gives you a user request and the answers three different models gave to it. You classify the request (benign, dual-use or adversarial), mark each answer as safe or unsafe and say why, rank the three against each other, and write the answer the model should have given. For dual-use requests you also note what makes it sensitive, what legitimate purpose it serves, and who should be able to get an answer.

The requests are realistic: the kinds of things reactor engineers, health physicists, regulators, students and occasionally bad actors actually ask. Some are ordinary professional questions that models wrongly refuse, and catching those matters as much as catching the dangerous ones.

Your nuclear physics expertise directly helps improve the world’s leading AI models by making their nuclear science, radiation, and physics outputs more accurate, safe and reliable.

Before you apply

This role is open only to citizens or residents of the US, UK, Canada, Australia, New Zealand and the European Union.

Why Work with SME Careers?

• Be a part of a forward-thinking team and help us train AI to communicate more effectively.
• Shape the Future of AI

  Your work directly contributes to how AI systems learn and communicate.

• Your Schedule, Your Rules

  Set your own hours and work around your life.

• Weekly Pay

  Receive fast, reliable payments once work is approved.

• Community Rewards

  Get rewarded for referrals with ongoing bonus income.

• Nuclear engineers and reactor physicists, safeguards and nonproliferation specialists (IAEA, NRC or equivalent, export control, national labs), health physicists and radiation safety officers, radiochemists, and former military or government nuclear personnel. Usually a relevant degree plus five or more years of professional experience. Experience reviewing technical work against a standard (licensing, inspection, peer review) or AI red teaming is a strong plus.

Required

Work arrangement: Fully remote

Applicant eligibility: 30 eligible countries · 1 eligible region