AI Red Team Specialist — Adversarial Testing (Remote)

Mercor is seeking responders for a remote AI safety red team. You will challenge conversational AI models with jailbreaks, prompt injections, and bias exploitation, producing high-quality data and reproducible reports for customers.

Ideal candidates have red teaming experience in AI or cybersecurity, are curious and structured, and can communicate risks clearly to technical and non-technical stakeholders. Remote work is available for this role.