Radiologicals Safety for Redteaming
Neon
$65 – $75 · as listed
Neon is seeking experienced radiological safety professionals for advanced red-teaming work on frontier AI models. Working remotely on this task-based project, you'll write specialized prompts designed to test how AI systems handle safety-critical scenarios in your domain. Your role involves crafting single-turn requests across multiple difficulty levels that evaluate whether models can distinguish between legitimate technical questions and genuinely dangerous requests, while maintaining helpful responses where appropriate.
This position suits professionals with deep expertise in radiological safety and a strong background in STEM fields. You'll contribute to AI safety research by helping identify potential vulnerabilities in how models handle sensitive technical information. The work is remote and available at the advanced level, with compensation listed at $65–$75 per hour.
From the listing: Mercor marketplace · task-based · 40h/week. 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 while answering legitimate questions fully while refusing genuinely dangerous ones. You will: - Write challenging single-turn prompts in your domain, labelled across three levels: benign
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 →