Lawrence Chan
Researcher at Alignment Research Center
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolLawrence Chan is a researcher focused on evaluating and aligning large language models, currently working at the Alignment Research Center after a stint at Redwood Research where he built adversarial training methods and tools for neural network interpretability. He holds a PhD-level background from UC Berkeley’s Center for Human Compatible AI and has spent over a decade applying statistical and CS training—from a dual BS in Statistics and Computer Science at Penn—to concrete safety problems in modern ML. Lawrence combines rigorous theoretical thinking about value alignment with hands-on empirical evaluations of LLM behavior, bridging conceptual frameworks and attack-driven assessments. Based in the San Francisco Bay Area, he brings a rare mix of academic depth and engineering pragmatism, with experience spanning research assistance roles in academic labs to production-oriented safety work at industry labs.
11 years of coding experience
4 years of employment as a software developer
High School, 4.3/4.5, High School, 4.3/4.5 at 上海中学国际部Bachelor of Science, Business (Statistics) and Computer Science, 3.86, Bachelor of Science, Business (Statistics) and Computer Science, 3.86 at University of Pennsylvania
English, Chinese
Github Skills (18)
softmax10
pointer9
threshold8
jekyll-theme5
jekyll5
deep-learning4
tensorflow4
infer3
julia2
planning2
hyperbolic2
python1
uss1
language-model1
webppl1
Programming languages (4)
Github contributions (5)
Chanlaw/pointer-networks
Aug 2016 - Dec 2016
Contributions:62 commits, 66 pushes in 3 months
deep-learningthresholdmodifiedpointertensorflow
Chanlaw/prediction-extraction
May 2016 - Sep 2016
Contributions:21 commits, 15 pushes, 1 branch in 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.