Summary
Tianle Li is a machine learning engineer and CS PhD candidate at UC Berkeley with eight years of hands-on experience building and scaling large language models and RL systems. Currently a Member of Technical Staff at Thinking Machines Lab after co-creating and leading post-training RL and model-merging efforts on Grok releases at xAI, he focuses on the hardest problems between current models and superintelligence. His background spans industry R&D (xAI, Nexusflow, Google), tools and deployment (AMD, enterprise APIs), and platform-building research like Chatbot Arena at Berkeley Sky Computing Lab. Comfortable moving between research and production, he has led distillation, RL fine-tuning, and scaling efforts that bridge paper ideas to deliverable models. Notably, he blends academic rigor from Berkeley EECS with pragmatic engineering—often preferring to “make models cracked” through adversarial training and clever post-training interventions.
8 years of coding experience
3 years of employment as a software developer
Bachelor of Science - BS, Electrical Engineering and Computer Science, Bachelor of Science - BS, Electrical Engineering and Computer Science at University of California, Berkeley
High School Diploma, High School Diploma at Esperanza High School
Chinese, English, Japanese