Consigue una respuesta de este empleador
Tu currículum y tu carta de presentación, adaptados exactamente a lo que buscan contratar.
Softechub is seeking Nuclear Engineering & Safeguards Experts to join a panel that will red-team frontier AI models. You will craft challenging single-turn prompts at three levels: benign, dual-use, and adversarial, to assess misuse potential while ensuring legitimate questions are answered properly.
The role involves assembling and contributing to a global, task-based evaluation effort that tests model judgment on technical requests and safeguards.
$65 - $75/task worldwide Posted 58 days ago
About the work the team is assembling a panel of nuclear 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-use, and adversarial.