Christian Sigg
Software Engineer at Google
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolChristian Sigg is a Swiss software engineer with over a decade of experience in high-performance compiler and GPU backend development, currently at Google after an extensive tenure at NVIDIA. He specializes in ML compiler toolchains and GPU runtimes, with significant open-source contributions to flagship projects like JAX, TensorFlow/XLA, MLIR, Triton, and LLVM. His work spans CUDA runtime integration, PTX generation, autotuning and memory management, and pragmatic build-system fixes that keep large codebases portable across CUDA and compiler versions. Christian combines deep academic training (MS and PhD from ETH Zürich in computational science and graphics) with hands-on performance engineering, having developed simulators and real-time physics at NVIDIA earlier in his career. Colleagues rely on him for careful refactors and subtle correctness fixes that improve maintainability and cross-platform GPU support. He has a knack for addressing obscure compiler-toolchain and GPU interoperability issues that quietly unlock performance for ML workloads.
10 years of coding experience
10 years of employment as a software developer
MS, Computational Science and Engineering, MS, Computational Science and Engineering at ETH Zürich
Github Skills (42)
c-language10
gpgpu10
batching10
preprocessing10
back-end-development10
python10
preprocess10
llvm10
tensorrt10
gpu-programming10
machine-learning10
c-preprocessor10
build-system10
mlr10
kernel10
Programming languages (10)
Github contributions (5)
openxla/xla
Jul 2019 - Jan 2023
A machine learning compiler for GPUs, CPUs, and ML accelerators
Role in this project:
Back-end Developer
Back-end DeveloperContributions:15 reviews, 152 commits, 26 comments in 3 years 6 months
Contributions summary:Christian primarily worked on the XLA compiler, focusing on improving code generation and compiler features. Their contributions included addressing compiler limitations, optimizing code for better performance, and fixing issues related to build configurations. The user also contributed to the TFRT backend implementation of XLA. Furthermore, the user added new features such as lowering of linalg.generic to GPU.
compilercommunity-drivenmachine-learningmodular
llvm/llvm-project
Jan 2020 - Feb 2025
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:Back-end Developer
Back-end DeveloperContributions:23 reviews, 60 PRs, 317 pushes in 5 years 2 months
Contributions summary:Christian primarily contributed to fixing build issues related to Bazel configuration files within the LLVM project. Their work involved modifying `BUILD.bazel` files for various components like MLIR and Clang, ensuring correct dependencies and configurations. They also addressed deprecation warnings by refactoring code to use free function calls instead of member functions for casting and other operations. These changes indicate a focus on build system maintenance and code modernization within the compiler infrastructure.
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.