Mercor is assembling a panel of experts to red-team frontier AI models, focusing on the misuse potential of technical requests. You will write prompts at three levels—benign, dual-use and adversarial—and evaluate model responses against a defined policy standard.
A solid emphasis on clear written rationale is required, with samples or links to prior work. The role targets licensed practitioners who handle specialty materials and sign for them, with emphasis on distinguishing routine
#J-18808-Ljbffr
📌 Licensed Blasting Engineer for AI Risk Red-Team (Sydney)
🏢 Mercor
📍 Sydney
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.