Researcher, Misalignment Monitoring Lead

What you'll do

• Set research priorities and lead rigorous evaluations of monitor effectiveness and failure modes.
• Develop methods and tools to stress-test monitors, investigate false positives and missed detections, and measure performance as model capabilities evolve.
• Translate research findings into practical safety improvements with research and engineering teams.

What they ask for

• Strong background in machine learning research, particularly in model evaluations, AI safety, alignment, robustness, or related areas.
• Demonstrated ability to lead technically challenging research projects from question definition through experimentation and results.
• Strong experimental judgment and ability to design rigorous, reproducible evaluations that are difficult to game.
• Hands-on experience building or evaluating machine learning systems, including large language models or other frontier AI systems.

Nice to have

• Experience with AI monitoring, automated evaluations, adversarial testing, or red-teaming.
• Research in scalable oversight, AI control, model behavior analysis, or interpretability.

Pay

$380K – $500K USD base salary

Tools

machine learning, large language models

AI focus

Research on monitoring frontier AI systems for misalignment, including evaluating monitor reliability, detecting failures, and improving oversight.