Role OverviewMercor is seeking an AI Safety Expert - Red Team to connect elite creative and technical talent with leading AI research labs. The role involves red teaming conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
What You Will Do
Responsibilities include generating high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks. The role also involves applying structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
Why It Might Be a Fit
The ideal candidate will have prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing) and be able to explain risks clearly to technical and non-technical stakeholders.
Requirements
- Fluent in English and Gujarati
- Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing)
- Ability to explain risks clearly to technical and non-technical stakeholders
]]>