Chris (Zhizhou) Zhang

I am Chris (Zhizhou) Zhang, 张之洲, a software engineer at Uber's Frontier Tech Labs (FTL).

My main focus is Perf Factory, an effort to automate performance analysis and optimization across Uber’s services. The work brings together profiling, compiler optimizations, and distributed tracing.

Talks Publications Background Google Scholar

Current Work

Profiling Always-on profiling across Uber's 6,000+ services, built with colleagues at Uber and Grafana, to understand CPU use, memory allocation, and lock contention.

Compiler optimization Using runtime profiles to guide compiler optimizations, including Go PGO, and integrating optimization into production build and deployment workflows.

Distributed tracing Using traces and critical path analysis, as in CRISP, to identify which services and operations contribute to end-to-end latency.

I'm working on bringing these tools into agent workflows that investigate bottlenecks, propose optimizations, and check their effects on performance and program behavior.

I also work on automated program repair, combining program analysis and machine learning to find and fix data races, resource leaks, and other software defects.

Engineering

May 2025

Selected Publications

DR. FIX: Automatically Fixing Data Races at Industry Scale
PLDI 2025
The Tale of Errors in Microservices
SIGMETRICS 2025
CRISP: Critical Path Analysis of Large-Scale Microservice Architectures
USENIX ATC 2022
Optimistic Concurrency Control for Real-world Go Programs
USENIX ATC 2021

Background

I received my Ph.D. in Computer Science from UC Santa Barbara, where I was advised by Prof. Tim Sherwood at ArchLab and closely collaborated with Prof. Jonathan Balkind. Before that, I received my undergraduate degree from the University of Rochester, where I worked with Prof. Chen Ding.

Outside Work

In my spare time, I enjoy hiking and playing violin.