Una candidatura completa en un minuto
Currículum y carta de presentación personalizados, listos para enviar.
Softechub is assembling a panel of radiological safety experts to red-team frontier AI models. You will write challenging, domain-specific single-turn prompts labelled across benign, dual-use, and adversarial levels, testing whether models can discern misuse while answering legitimate questions.
This is a remote, global opportunity posted for task-based compensation. Ideal candidates have domain expertise in radiological safety and prompt design, with the ability to clearly label prompts and
$65 - $75/task worldwide Posted 58 days ago
The team 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 challenging single-turn prompts in your domain, labelled across three levels: benign, dual-use, and adversarial.