Researcher, Frontier Risk Mitigations

📋 Description

• Identify emerging AI safety risks and mitigate their impact
• Develop evaluations to assess risks, collaborating with domain experts
• Set research directions to make AI systems safer and more robust
• Contribute to best practices for AI safety industry-wide
• Evaluate red-teaming pipelines to test end-to-end safety

🎯 Requirements

• 2+ years in AI safety, RLHF, or related fields
• PhD or degree in CS, ML, or related field
• Experience with large-scale AI systems
• 4+ years of research engineering, Python or similar language

🎁 Benefits

• Equity and salary compensation
• Competitive equity value and cash salary