12 Oct
|
Mercor
|
Canberra
Mercor is assembling a remote AI safety red team to probe and strengthen your conversational AI systems. This role focuses on adversarial testing across topics like bias, misinformation, and safety, with participation in higher-sensitivity projects optional and guided by explicit wellbeing resources.
You will annotate vulnerabilities, generate high-quality data, and document outcomes in reproducible reports to help customers improve their AI safety posture.
#J-18808-Ljbffr
📌 AI Safety Red Team Specialist (Canberra)
🏢 Mercor
📍 Canberra