Tianle Li
Berkeley, California, United States
Summary
🤩
RockstarTianle Li is a Member of Technical Staff at xAI and co-creator of Grok 4 Fast, where he led post-training RL work and co-led distillation to move large models into compact, aligned deployments. A UC Berkeley EECS student and LMSYS researcher at the Berkeley Sky Computing Lab, he blends academic rigor with hands-on industry experience from roles at Google, Nexusflow, AMD and other internships. Over five years he has specialized in LLM training, alignment, and model compression while shipping production-focused ML systems. He also produced technical content on YouTube, a background that sharpens his ability to communicate complex research to broader audiences. Based in Berkeley, he focuses on the practical safety and scaling challenges that stand between current models and superintelligence.
5 years of coding experience
Github Skills (4)
vitis7
fpga6
composer4
php4
Programming languages (5)
Github contributions (5)
lmarena/arena-hard-auto
Mar 2024 - Mar 2025
Arena-Hard-Auto: An automatic LLM benchmark.
Contributions:1 review, 16 PRs, 100 pushes in 11 months
CodingWithTim/CAS
Feb 2022 - Apr 2023
Contributions:1 push, 1 branch in 1 year 2 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.