Radiation Safety Officer
Neon
$65 – $75 · as listed
Neon is seeking an intermediate-level Radiation Safety Officer to contribute to AI safety testing on a remote, task-based arrangement. In this role, you'll write specialized prompts designed to evaluate how AI models handle requests in radiological safety and related STEM domains. Your work involves crafting scenarios across difficulty levels that test whether AI systems can distinguish between legitimate technical questions and requests with genuine misuse potential—approving appropriate queries while correctly refusing harmful ones. This is writing-focused work that draws on your expertise to improve model safety.
This position suits professionals with solid grounding in radiation safety who can think critically about dual-use risks and communicate technical concepts clearly. You'll work independently at your own pace, with compensation listed at $65–$75 per task or unit, depending on scope and complexity. No special equipment beyond a computer and internet connection is required.
From the listing: Mercor marketplace · task-based. ## About 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, dua
Applications are completed on the listing’s own site. Pay is shown as posted by the source (“as listed”) or the aggregator’s estimate where marked — offers and availability change, and individual results vary.
Want help getting selected — and finding the best-paid work for your country? See how membership works →