AI Trainer Jobs is seeking a bilingual Chinese Generalist Expert for a remote AI safety red-team role focused on stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and pair each jailbreak with the violated rubric clause so the safety team can patch the gap.
Adversarial evaluation helps harden models before customers see them. You’ll think like attackers, write up rigorous failures, and help reproduce, fix, and regress-test the model.
#J-18808-LjbffrRemote AI Safety Red Team Specialist — Bilingual Chinese in Remote at Unknown Company
This position is listed as full time and able to be worked remotely.