Researcher, Misalignment Monitoring Lead

📋 Description

• Lead the research and technical direction for evaluating and improving the misalignment monitoring
• Design and execute rigorous evaluations that measure monitor effectiveness, identify failure modes
• Develop methods to stress-test and red-team monitors, including identifying behaviors that evade
• Investigate false positives, missed detections, and other monitoring failures to improve the
• Build scalable evaluation frameworks and experimental tools that enable ongoing measurement of
• Translate research findings into actionable improvements, working with partner teams to strengthen

🎯 Requirements

• Have a strong background in machine learning research, particularly in model evaluations, AI
• Have demonstrated the ability to lead technically challenging research projects, from identifying
• Bring strong experimental judgment and understand how to design evaluations that are rigorous
• Have hands-on experience building or evaluating machine learning systems, including working with
• Enjoy investigating complex failure modes and developing methods to distinguish meaningful safety
• Are comfortable working on open-ended research problems where the right methodology or success

🎁 Benefits

• Base salary range: $380K – $500K
• Equity compensation