Researcher, Misalignment Monitoring Lead
Core
Lead research and technical execution on misalignment monitoring for frontier AI systems, evaluating monitor effectiveness and reliability.
Role type
Senior IC machine-learning researcher (AI safety/alignment)
Builds
Scalable evaluation frameworks, experimental tools, and stress-testing methods for AI monitors
Domain
Artificial Intelligence / AI Safety / Alignment
Deliverable
production ML models
Required skills
Machine learning research, model evaluations, AI safety, alignment, robustness, experimental design, large language models, failure mode analysis, technical research leadership
Preferred skills
AI monitoring, automated evaluations, adversarial testing, red-teaming, scalable oversight, AI control, model behavior analysis, interpretability, technical research leadership, mentoring
Technologies
Large language models, AI monitoring systems, evaluation frameworks
Responsibilities
Lead research direction for misalignment monitoring, design rigorous evaluations of monitor effectiveness, develop stress-testing and red-teaming methods, investigate monitoring failures, build scalable evaluation tools, translate findings into safety improvements, establish research priorities
Seniority
Senior, hands-on IC
