Alex Baden
Senior AI Compilers Engineer at Kernelize
Raleigh-Durham-Chapel Hill Area United States
Summary
🤩
Rockstar🎓
Top SchoolAlex Baden is a Senior AI Compilers Engineer with 11 years of experience designing high-performance systems across compilers, parallel programming, distributed databases, ML frameworks, and graphics. He specializes in heterogeneous CPU/GPU co-design and accelerator performance tuning, with hands-on work improving Triton and PyTorch backends and driving Intel-specific MLIR/LLVM pipeline enhancements. Alex thrives in large, complex codebases—shipping features, refactoring for correctness, and extracting measurable performance gains under tight deadlines. He led core query-engine architecture and GPU acceleration work at OmniSci and contributed upstream to well-known open-source projects like PyTorch and Google’s Neuroglancer. Known for bridging low-level compiler passes to practical developer guidance, he combines deep architecture intuition with a user-focused approach to engineering. Based in the Raleigh-Durham area, he pairs rigorous academic training from Johns Hopkins with a knack for untangling gnarly performance problems.
11 years of coding experience
11 years of employment as a software developer
Johns Hopkins UniversityBachelor of Science (B.S.) Mathematics, Bachelor of Science (B.S.) Mathematics at University of Maryland
Stackoverflow
11reputation
116reached
1answer
1question
Github Skills (27)
pytorch10
javascript10
python10
back-end-development10
compiler-development10
testing10
machine-learning10
typescript10
mlr10
triton10
gpu10
typescript-types10
typescripts10
decode9
webgl9
Programming languages (16)
Github contributions (5)
google/neuroglancer
Jan 2017 - Jan 2018
WebGL-based viewer for volumetric data
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:52 commits, 17 PRs, 32 comments in 1 year
Contributions summary:Alex contributed to the `google/neuroglancer` repository by implementing and improving various features. Their work included adding a transposeArray2d function with unit tests, supporting 3-channel JPEG images, adding support for tiles from the Render web service, and fixing an issue related to transpose arguments when decoding a JPEG stack. The user also refactored existing code and added new features like support for multi-scale chunks, and added various quality of life improvements.
webgl
triton-lang/triton
May 2024 - Mar 2026
Development repository for the Triton language and compiler
Role in this project:Back-end Developer
Back-end DeveloperContributions:5 reviews, 14 PRs, 21 comments in 1 year 10 months
Contributions summary:Alex primarily contributed to the Triton language and compiler, focusing on backend and runtime aspects. Their work included improving Python compatibility, specifically addressing dictionary merging and Python version support. The user also added functionality for stacktrace handling and integrated new testing for boolean data type handling. They demonstrated expertise in areas of layout verification and backend compilation testing.
compiler
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.