Hyojun Kim - Software Engineer at Google

Hyojun Kim

Software Engineer at Google

San Jose, California, United States

Join Prog.AI to see contacts

Summary

👤

Senior

🎓

Top School

Hyojun Kim is a software engineer and Ph.D. in computer science specializing in storage systems, flash memory software, and Cassandra, with 13+ years of industry experience and a strong research foundation. He has held roles from flash translation layer developer at Samsung to research staff at IBM Research and principal engineer at Datos IO, and has been at Google since 2016 driving backend systems. His work spans production engineering and rigorous research—10+ top conference publications and 13+ US patents reflect a talent for turning deep systems ideas into practical products. On GitHub he contributes to high-profile projects like XLA and TensorFlow Runtime, improving compilation, TPU support, and core runtime test coverage. Based in San Jose, he combines low-level storage expertise with modern ML runtime engineering, enabling performance and reliability across storage and accelerator stacks. Colleagues rely on him for careful, impact-focused engineering that bridges academic rigor and production-scale systems.

8 years of coding experience

11 years of employment as a software developer

Bachelor's degree, Electrical and Electronics Engineering, Bachelor's degree, Electrical and Electronics Engineering at Sogang University

Doctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at Georgia Institute of Technology

Master's degree, Electrical, Electronics and Communications Engineering, Master's degree, Electrical, Electronics and Communications Engineering at Hanyang University

English, Korean

Stackoverflow

Stats

1reputation

0reached

0answers

0questions

Github Skills (10)

unit-testing10

xla10

compiler10

compiler-design10

c-language10

cprogramming-language10

performance-optimization10

tpu10

reference-counting9

caching9

Programming languages (3)

C++CPython

Github contributions (5)

tensorflow/runtime

Nov 2020 - Sep 2022

A performant and modular runtime for TensorFlow

Role in this project:

Back-end Developer & Test Automation Engineer

Contributions:57 commits, 1 comment in 1 year 10 months

Contributions summary:Hyojun contributed to the TensorFlow Runtime project by adding and improving unit tests. Their work focused on creating and refining tests for core components like `ReferenceCounted`, `RCReference`, and `BefReader` classes. The user also updated tests for the `HostBuffer` and `Location` classes, indicating a focus on ensuring the stability and reliability of fundamental runtime functionalities. These contributions are critical for verifying the correctness and maintainability of the TensorFlow runtime.

runtimeperformantmodulartensorflow

openxla/xla

May 2021 - May 2022

A machine learning compiler for GPUs, CPUs, and ML accelerators

Role in this project:

Back-end Developer

Contributions:7 commits in 1 year

Contributions summary:Hyojun primarily contributed to XLA's backend functionality, making changes related to compilation, caching, and TPU integration. They modified existing code to incorporate features like autofdo fingerprinting, and profile versions, and compilation cache keys to improve the build process. These changes were mainly focused on enabling and improving compilation and performance for TPU hardware. Furthermore, the user refactored the profile handling by changing the passing mechanism from explicit arguments to embedding in the HloModule.

compilercommunity-drivenmachine-learningmodular

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