Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. You will write challenging single-turn prompts in your domain, labelled across three levels: benign, dual-use, and adversarial.
You will also evaluate the responses and write the reference answer with the technical reasoning behind it. This role requires rigorous written justification and a solid background in licensing, inventory, and regulatory compliance.
J-18808-Ljbffr