Summary
Tianle Cai is an ML-focused PhD candidate at Princeton with nine years of research and industry experience accelerating large-model inference and co-designing model, algorithm, and systems stacks. He has driven applied research at Together AI, Google DeepMind, and Microsoft, contributed to high-impact open-source projects like FasterDecoding (Medusa, BitDelta) and LLM-ToolMaker, and interned on VisionPro at Apple. Combining dual undergraduate degrees in Computer Science and Applied Mathematics from Peking University with visiting research stints at MIT and UC Berkeley, he blends rigorous theory with systems-first engineering. A life-long learner, hacker, and angel investor, he frequently bridges prototype research and production considerations to speed real-world ML deployment.
9 years of coding experience
5 years of employment as a software developer
Visiting Researcher Deep Learning Theory, Visiting Researcher Deep Learning Theory at University of California, Berkeley
Research Intern Learning Theory, Research Intern Learning Theory at Massachusetts Institute of Technology
Bachelor of Science - BS Computer, Bachelor of Science - BS Computer at Peking University
Doctor of Philosophy - PhD Search form Search Electrical and Computer Engineering, Doctor of Philosophy - PhD Search form Search Electrical and Computer Engineering at Princeton University