Hi, I am a software engineer at Google. My job is to make LLMs (e.g. Gemini and open-source LLMs) run more efficiently on TPUs.

Before joining Google, I received my PhD in Computer Science at the University of California, San Diego (UCSD), advised by Prof. Jishen Zhao. My PhD research spanned the intersection of machine learning (ML), computer architecture, and security. Earlier, I received my Master’s degree at the University of Michigan, Ann Arbor, advised by Prof. Hun-Seok Kim. I interned twice at Facebook AI Research (FAIR), supervised by Yuandong Tian and Hugh Leather.

Feel free to contact me via email.

Research Interests

My current research spans the large language model (LLM) stack:

• LLM Hardware-aware Optimization — quantization, pruning, and re-architecting
• LLM Post-training Algorithms — distillation, SFT, RL, and quality evaluation
• LLM Serving & Training Efficiency on TPU — model sharding, speculative decoding, and kernel optimization

Work Experience

Full-time

• Fall 2023 – Present: Software Engineer
  • Google, Sunnyvale, CA

Internships

• Summer 2022: Research Intern
  • Google, Sunnyvale, CA
• Summer 2021: Research Intern
  • Facebook AI Research (FAIR), Remote
• Summer 2020: Research Intern
  • Alibaba Cloud Computing Group, Seattle, WA
• Summer 2019: External Research Collaborator
  • Facebook AI Research (FAIR), Menlo Park, CA
• Summer 2018: Research Intern
  • Iluvatar CoreX, San Jose, CA