Remote AI Safety Red Team Specialist

Mercor is building a remote AI red team, focusing on safe and responsible testing of conversational systems. You will probe models with adversarial inputs, annotate vulnerabilities, and generate data to strengthen customer AI safety.

We value prior red-teaming experience, curiosity, and a structured, communicative approach. This role offers remote work with flexible collaboration across projects and clients.

#J-18808-Ljbffr…