Han-chung Wang is a compiler-focused software engineer with 11 years of experience building and optimizing ML compilers and accelerator tooling, currently a Member of Technical Staff at AMD after contributing to Google’s IREE compiler. He has deep practical experience in MLIR and LLVM back-end work, including integration test fixes, tensor/vector dialect adaptations, and sub-byte memref support—contributions to a widely used open-source compiler project. Comfortable bridging research and production, he has repeatedly shipped compiler features that reconcile low-level memory/shape semantics with accelerator constraints. Based in Seattle and educated at National Taiwan University, he brings a blend of systems-level rigor and hands-on debugging craft honed across internships and senior engineering roles.
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:
Back-end Developer
Contributions:529 reviews, 103 PRs, 197 pushes in 5 years 3 months
Contributions summary:Han-chung's contributions primarily involve modifying and fixing integration tests within the MLIR (Multi-Level Intermediate Representation) framework, specifically focusing on tensor and vector dialects. Their work includes adapting tests to accommodate changes in reshape and bitcast operations. The user also made improvements to the sub-byte type emulation support for memref operations, addressing issues related to dynamic offsets in multi-dimensional subviews. Furthermore, the user made changes to improve flattening vector.transfer_write operations.
Contributions:1 review, 2 PRs, 2301 pushes in 5 years
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.