Jinru He
Member Of Technical Staff at OpenAI
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolJinru He is a seasoned infrastructure and ML-serving engineer with over a decade of experience building high-throughput, low-latency systems for companies like Pinterest, Facebook, SHAREit, and Xiaohongshu, and is currently a Member of Technical Staff at OpenAI. He has led large-scale, multi-region, cloud-agnostic platform migrations and designed storage, caching, and scheduler systems that drove dramatic cost and utilization improvements (e.g., raising CPU utilization from 19% to 27% and saving hundreds of millions CNY). At Pinterest he built and led the ML serving platform that ranks tens of millions of objects per second and contributed to Teletraan, the company deploy system; at Facebook he worked on the Dragon distributed index serving 2M QPS. His background as an NYU PhD candidate in information retrieval and index optimization informs a rare blend of research rigor and production-grade engineering, especially in index/data-compression and query processing. Known for growing and leading large infra teams, he pairs hands-on C/C++/Python expertise with practical DevOps and Kubernetes experience to ship resilient, measurable systems.
10 years of coding experience
14 years of employment as a software developer
PhD Computer Science & Engineering, PhD Computer Science & Engineering at New York UniversityHigh school degree High school class, High school degree High school class at Yali High SchoolBachelor of Science Software Engineering, Bachelor of Science Software Engineering at Huazhong University of Science and Technology
English, Chinese, c++
Github Skills (5)
javas10
java10
metric10
opentsdb9
devops8
Programming languages (2)
Github contributions (3)
pinterest/teletraan
Jan 2016 - Aug 2016
Teletraan is Pinterest's deploy system.
Role in this project:
Backend & DevOps Engineer
Backend & DevOps EngineerContributions:148 commits, 76 PRs, 111 pushes in 6 months
Contributions summary:Jinru primarily focused on modifying backend services and infrastructure related to the deployment system. Their contributions included adding health check notifications, updating metrics endpoints, and incorporating new metrics to monitor. The user also updated the code to handle potential health check timeouts. Furthermore, the user updated the metrics write path.
dockerpinterest
jinruh/rocksplicator
Mar 2017 - Mar 2018
Contributions:1 push, 14 branches in 11 months
replicationrocksdb
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.