Ian Wood - Software Engineer at AMD

Ian Wood

Software Engineer at AMD

Bellevue, Washington, United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Ian Wood is a software engineer based in Bellevue with four years of experience focused on compilers, MLIR, and machine learning tooling. At AMD he works on IREE and MLIR back-end improvements, contributing fusion patterns and optimization passes to a production-grade ML compiler and runtime. His open-source contributions to high-profile projects like LLVM and IREE include canonicalization and crash fixes for Linalg/Tensor dialects and new tensor-shape optimization patterns that enhance compiler robustness and performance. Previously he built full-stack features and test harnesses at startups, translating SQL to Querydsl and adding backend test coverage, demonstrating a pragmatic balance of systems-level compiler expertise and product-oriented engineering.

4 years of coding experience

1 year of employment as a software developer

BS Computer Science, BS Computer Science at Northwestern University

Github Skills (8)

compiler-optimization10

c-language10

tensor10

lg10

cprogramming-language10

mlr10

llvm10

compiler9

Programming languages (5)

C#C++LLVMMLIRPython

Github contributions (5)

iree-org/iree

Apr 2024 - Apr 2025

A retargetable MLIR-based machine learning compiler and runtime toolkit.

Role in this project:

Back-end Developer & Compiler Engineer

Contributions:149 reviews, 256 PRs, 98 pushes in 11 months

Contributions summary:Ian's primary contribution focused on enhancing the IREE compiler, specifically within the Flow dialect. They implemented a new fusion pattern for generic ops generated by `gather` lowering, which improved the compiler's optimization capabilities. Furthermore, they added support for fusion operations for both `Linalg` and `LinalgExt` ops. Additionally, they extended functionality of existing passes.

mlirspirvvulkantensorflowcompiler

llvm/llvm-project

Apr 2024 - Apr 2025

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Role in this project:

Back-end Developer

Contributions:19 reviews, 41 PRs, 14 pushes in 11 months

Contributions summary:Ian contributed to the LLVM project by implementing and refactoring compiler optimization patterns. They focused on canonicalizing and optimizing operations within the MLIR dialect, specifically for the Linalg and Tensor dialects, and addressing crash issues. Their work included adding new patterns to convert and optimize tensor operations like expand and collapse shapes for improved performance and functionality. Additionally, they fixed a crash related to the linalg.transpose operation and improved the IntegerRangeAnalysis.

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