Yuda Fan
 |
Master Student Direct Doctorate Student Department of Informatik ETH Zürich |
About Me
I am a staff engineer of the AI Infra team, Rednote Hilab, leading algo-infra codesign. Particularly, I work on:
Overall improvment of inference throughput, latency and cost: distributed serving system, model execution runtime, and custom kernels.
Training native and hardware friendly techniques: quantization, speculative decoding, sparse attention, and etc.
From 2024 to 2026, I was working as a senior engineer at Hong Kong Research Center, expertising at LLM inference, high performance computing, and heterogeous computing.
I graduated from ETH Zürich with distiction in 2024. Prior to this, I obtained my Bechelor's degree with honor from ACM Honor Class, SJTU.
If you are interested in my educational background and research experience, please refer to my [CV](out-of-date, circa 2024) to get detail information.
For recruiters and hiring managers, I kindly invite you to take a look at this [resume] which highlights my working skills.