Obsidian is looking for a motivated professional to join their AI red team. The role involves probing AI models for vulnerabilities and generating data to ensure safety. You'll work on high-sensitivity projects involving bias, misinformation, and harmful behaviors, utilizing structured frameworks and documentation.
The ideal candidate will have prior red teaming experience, strong communication skills, and a curious mindset to tackle challenges head-on. This position offers the chance to directly impact AI safety and shape robust systems.
#J-18808-Ljbffr