Remote AI Safety Red Team Specialist
Summary
Probe AI conversational models with jailbreaks, prompt injections, and bias tests to uncover safety risks and generate actionable data for model hardening.
Mercor is seeking a bold AI red team specialist to probe conversational models with jailbreaks, prompt injections, and bias tests. This role is fully remote and focuses on generating actionable data to strengthen safety.
You will document findings, follow established taxonomies, and collaborate with clients to clarify risks. Prior red-teaming in AI, cybersecurity, or socio-technical domains is preferred.