Zhenan Fan is a Staff Research Engineer at Huawei Vancouver Research Center with 8 years of experience building production-grade, cloud-native LLM inference and distributed serving systems. He leads cross-functional teams delivering SLO-aware scheduling, elastic MoE, multi-LoRA and multimodal serving pipelines optimized for Ascend NPUs and Huawei Cloud ModelArts. His background bridges rigorous optimization research—PhD from UBC on duality and federated learning—with hands-on system engineering, contributing to Huawei’s Pangu and the OptVerse solver. Published at top AI and data conferences, he combines applied research with operational impact, often turning algorithmic insights into scalable, fault-tolerant inference features. An interesting thread in his work is the focus on disaggregation patterns (Encode–Prefill–Decode, MoE–Attention) that enable fine-grained autoscaling and resilience in multi-tenant LLM deployments.
8 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at The University of British Columbia
Honours Bachelor of Science, Specialist in Mathematics; Major in Statistics and Computer Science, CGPA 3.95, Honours Bachelor of Science, Specialist in Mathematics; Major in Statistics and Computer Science, CGPA 3.95 at University of Toronto
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Zhenan Fan - Staff Research Engineer at Huawei Canada