
I am currently at Snowflake AI Research, where I lead the development of Arctic Inference and contributed to training Arctic, a 480B sparse MoE LLM. My research interests lie broadly in efficient ML systems, algorithms, and architectures. Previously, I served as the CEO of Petuum and received my PhD in Computer Science from Carnegie Mellon University, where I was supervised by Eric Xing.
Before getting into ML systems, I studied Computer Science and Combinatorics & Optimization at the University of Waterloo, where I worked on improving Quicksort with J. Ian Munro and Alejandro Lopez-Ortiz. I also participated in competitive programming, and won a gold medal at the International Olympiad in Informatics (IOI).
Email: contact (at) [my first name] (dot) net
SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
[paper]
[code]
[blog]
Gabriele Oliaro, Zhihao Jia, Daniel Campos, Aurick Qiao.
NeurIPS’25 Spotlight ⭐
SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation
[paper]
[code]
[blog]
Aurick Qiao, Zhewei Yao, Samyam Rajbhandari, Yuxiong He.
EMNLP’25
LLM360: Towards Fully Transparent Open-source LLMs
[paper]
[website]
Zhengzhong Liu, Aurick Qiao, Willie Neiswanger, Hongyi Wang, Bowen Tan, Tianhua Tao, Junbo Li, Yuqi Wang, Suqi Sun, Omkar Pangarkar, Richard Fan, Yi Gu, Victor Miller, Yonghao Zhuang, Guowei He, Haonan Li, Fajri Koto, Liping Tang, Nikhil Ranjan, Zhiqiang Shen, Xuguang Ren, Roberto Iriondo, Cun Mu, Zhiting Hu, Mark Schulze, Preslav Nakov, Tim Baldwin, Eric P Xing.
COLM’23
Pollux: Co-adaptive Cluster Scheduling for Goodput-optimized Deep Learning
[paper]
[code]
Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, Eric P Xing.
OSDI’21 Best Paper Award ⭐
Managed Communication and Consistency for Fast Data-parallel Iterative Analytics
[paper]
[code]
Jinliang Wei, Wei Dai, Aurick Qiao, Qirong Ho, Henggang Cui, Gregory R Ganger, Phillip B Gibbons, Garth A Gibson, Eric P Xing.
SoCC’15 Best Paper Award ⭐