Mercor seeks a remote AI red-team specialist to probe conversational models, uncover vulnerabilities, and generate high-quality adversarial data. You will annotate failures, classify risks, and report findings to strengthen customer AI systems.
Ideal candidates bring experience in AI safety, cybersecurity or socio-technical probing, and can structure testing with established playbooks and frameworks while communicating risks clearly to diverse stakeholders.
#J-18808-Ljbffr…
