Chemicals Safety for Redteaming
Neon
$65 – $75 · as listed
Neon is seeking advanced chemistry experts to participate in red-teaming exercises for frontier AI models. As part of a specialized panel, you'll write targeted prompts that test whether AI systems can accurately distinguish between legitimate scientific inquiries and requests with potential safety risks. Your work involves crafting single-turn prompts across varying difficulty levels, each carefully labeled to help evaluate model behavior in chemistry-related scenarios.
This remote position suits STEM professionals with deep chemistry knowledge who can think critically about dual-use concerns and AI safety. The role is task-based and structured around approximately 40 hours per week. You'll be contributing directly to AI training and safety validation work—helping ensure frontier models respond appropriately to sensitive domain-specific requests.
Compensation is listed at $65–$75 per hour. This advanced-level opportunity is ideal for chemists, researchers, or domain specialists interested in AI alignment and responsible AI development.
From the listing: Mercor marketplace · task-based · 40h/week. About the work Mercor is assembling a panel of chemistry domain 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, dual-u
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 →