Role OverviewAs an AI Safety Expert, you will be part of Mercor's team, connecting elite creative and technical talent with leading AI research labs. Your role will involve red teaming conversational AI models and agents, focusing on jailbreaks, prompt injections, misuse cases, and bias exploitation.
What You Will Do
Your responsibilities will include generating high-quality human data, annotating failures, classifying vulnerabilities, and flagging systemic risks. You will also apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
Why It Might Be a Fit
We are looking for individuals with prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing, as well as the ability to explain risks clearly to both technical and non-technical stakeholders.
Requirements
- Fluent in English & Indonesian
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Ability to explain risks clearly to both technical and non-technical stakeholders
Benefits
]]>