关于
I am a Research Engineer at the Azure Research – Systems (opens in new tab) group where I work on improving the efficiency of Microsoft’s AI infrastructure.
I obtained my PhD in Computer Science from UIUC with a thesis on cloud systems management with efficient and robust online learning. My work is in the intersection of systems and machine learning. Examples include:
- Energy efficient, SLO-aware LLM serving: ATC24 (opens in new tab), AIOps24 (opens in new tab), SoCC24 (opens in new tab)
- Robust, at-scale ML model deployment in cloud systems: ATC23 (opens in new tab), NeurIPS23 (opens in new tab), MLSys24 (opens in new tab)
- Multi-tenant serverless computing resource management: SoCC22 (opens in new tab), NeurIPS22 (opens in new tab), EuroMLSys22 (opens in new tab)
- SLO-oriented resource management for cloud microservices: OSDI20 (opens in new tab)