Mercor is assembling a remote red team for AI safety testing. You will probe conversational AI models for jailbreaks, prompt injections, and misuses while generating high-quality human data and reproducible reports.
The role emphasizes structured, framework-based testing, explicit communication of risks to both technical and non-technical stakeholders, and adaptability across projects and customers.
#J-*****-Ljbffr
📌 Remote Ai Safety Red Team Specialist (Sydney)
🏢 Mercor
📍 Sydney