Hu Jiefu

Seoer at Tencent

Shenzhen, Guangdong Province, China
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Hu Jiefu is a backend and performance-focused software engineer with seven years’ experience, currently working at Tencent in Shenzhen. He contributes to high-performance open-source projects like vllm—optimizing CPU inference paths, adding AVX2 support and profiling hooks—and has deep systems knowledge from contributions to OpenJDK and LLVM. His work spans low-level JVM runtime improvements, compiler cleanups, and CI/build adaptations for non-AVX512 environments, reflecting a strong emphasis on portability, tooling, and reliable builds. Comfortable debugging complex system software, he pairs careful code hygiene with pragmatic performance fixes that reduce future maintenance costs. Colleagues would note his knack for surfacing subtle platform issues (missing error messages, container-aware logs) that improve observability and deployability at scale.
code7 years of coding experience
github-logo-circle

Github Skills (33)

pytorch10
c-language10
jvm10
intel10
python10
compiler-development10
llvm10
avx10
inference10
java10
llm10
javas10
openjdk10
optimisation10
transformer10

Programming languages (4)

JavaC++LLVMPython

Github contributions (5)

github-logo-circle
openjdk/jdk

Sep 2020 - Jan 2025

JDK main-line development https://openjdk.org/projects/jdk
Role in this project:
userBack-end Developer
Contributions:330 reviews, 205 PRs, 1199 comments in 4 years 5 months
Contributions summary:Hu contributed to the OpenJDK project, specifically the JDK main-line development repository. Their work focused on modifying and improving low-level components related to the Java Virtual Machine (JVM) and its interaction with the operating system, including changes to runtime stubs, and container information in the error log, as well as comment improvements. The user's contributions indicate a focus on performance optimization and system-level debugging within the JVM. They also made contributions to the test suite, demonstrating a proficiency in testing and debugging complex system software.
openjdkjavajvmjdk
llvm/llvm-project

Jan 2023 - Mar 2025

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:
userBack-end Developer
Contributions:1 review, 2 PRs, 284 pushes in 2 years 2 months
Contributions summary:Hu primarily focused on fixing compiler warnings related to unused variables, functions, and deprecated features within the LLVM project. Their contributions span multiple subprojects within LLVM, including flang, mlir, clang, and X86, indicating a broad understanding of the project's codebase. The fixes involved code cleanup and adherence to stricter coding standards, improving code quality and potentially reducing future debugging efforts. They also addressed some build failures and updated deprecated code.
compilerstechnologiesclangsubmittoolchain
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
Hu Jiefu - Seoer at Tencent