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 prompts at three levels (benign, dual-use, adversarial), evaluate model responses, and craft the reference answer with detailed reasoning for how to respond correctly.
#J-18808-Ljbffr
Radiation Safety Officer — AI Model Red-Teaming Lead in Toronto employer: Mercor
Mercor is an exceptional employer that fosters a dynamic and innovative work culture, connecting top-tier talent with leading AI research labs. With the flexibility of remote work, employees enjoy a supportive environment that encourages professional growth and collaboration across diverse teams. The competitive compensation and the opportunity to engage in high-impact projects make Mercor a rewarding place for legal experts looking to make a meaningful contribution.
