锦鲤求职岗位描述
岗位职责
"• Drive research on AI model safety and alignment
• Develop safety evaluation and risk mitigation frameworks for AI models
• Ensure AI systems meet ethical standards and regulatory requirements
• Build a comprehensive AI safety defense system to surface and address emerging risks"
岗位要求
"• 3+ years in AI safety or ML research; deep understanding of large model risks and ethical considerations
• Expert in red teaming, adversarial attack & defense, and model interpretability
• Able to independently build a comprehensive AI safety evaluation framework and author safety/alignment technical reports
• Strong cross-functional communicator — comfortable partnering with legal and compliance teams"