Mike Lee
Research Scientist @Scale AI
Signup · Get unlimited contacts
WORK HISTORY
Research Scientist @Scale AI
San Francisco, CA, US
Evaluations and human oversight of AI with Scale\'s Safety, Evaluations and Alignment Lab (SEAL)
EDUCATION
Carnegie Mellon University
Master’s Degree, Robotics
Princeton University
Bachelor of Science (B.S.), Mechanical & Aerospace Engineering
Carnegie Mellon University
Doctor of Philosophy - PhD, Computer Science (specialized in Robotics and AI)
SKILLS
ABOUT MIKE LEE
I research how to evaluate whether AI systems can reason carefully through decisions that require judgment (moral dilemmas, cross-cultural safety, underspecified questions), know when they\'re out of their depth, and can interact with humans accordingly.I build benchmarks and evaluation methodologies for AI safety and alignment. Current projects span procedural moral reasoning assessment, national security safety evaluation for multilingual LLMs, and clarification behavior in long-horizon autonomous agents.This builds on my PhD research in human-AI interaction, where I developed algorithms for personalized, transparent AI decision-making — adapting curricula of demonstrations to a human\'s current understanding to enable more effective collaboration with intelligent systems.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.