Kurt Mohler
Software Engineer at OpenTeams
Vancouver, British Columbia, Canada
Summary
🤩
Rockstar🎓
Top SchoolKurt Mohler is a software engineer with 11 years of experience building high-performance systems and developer tools, currently based in Vancouver and working at OpenTeams. He has a strong background in performance analysis and embedded/parallel computing from roles at Samsung Austin R&D and KNUPATH, where he designed toolchains, hand-optimized assembly, and scalable algorithms for heterogeneous architectures. From 2019 to 2025 he contributed to PyTorch at Quansight, adding meta-device support to core storage classes and addressing subtle storage-edge cases in a leading deep learning framework. Kurt combines low-level systems expertise with practical web and tooling experience, having shipped visualization and trace-analysis tools that accelerated CPU simulation workflows. He’s curious by nature and focused on creative, optimal solutions—equally comfortable modifying C++ internals of ML runtimes or architecting workload compression and analysis pipelines. An attention to detail and performance-first mindset quietly drive his contributions to widely used open-source projects.
11 years of coding experience
10 years of employment as a software developer
Bachelor of Science (BS) Computer Engineering, Bachelor of Science (BS) Computer Engineering at University of Pittsburgh
Stackoverflow
421reputation
17kreached
6answers
0questions
Github Skills (14)
pytorch10
tensor10
python10
gpu9
cprogramming-language9
machine-learning9
c-language9
deep-learning9
neural-network6
reproducible-research6
deterministic6
embedding6
autograd6
backpropagation6
Programming languages (6)
Github contributions (5)
pytorch/pytorch
Dec 2019 - Jan 2023
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:
Back-end Developer
Back-end DeveloperContributions:624 reviews, 207 commits, 290 PRs in 3 years 1 month
Contributions summary:Kurt's commits focus on enhancing the PyTorch library's functionality by adding and supporting meta device support to `_UntypedStorage` and `_TypedStorage` classes. This involved modifying and testing code within `test/test_torch.py` and `torch/storage.py`, introducing new functionalities in C++ code, and ensuring compatibility with existing functionalities. The user's work enables the use of "meta" devices within the PyTorch framework, likely enabling more efficient memory usage or other performance enhancements within the PyTorch ecosystem. The user addressed several potential errors related to storage in PyTorch.
pythongpu-accelerationdeep-learninggpunumpy
kurtamohler/spacetimelib
Jul 2022 - Sep 2023
Special relativity tool
Contributions:2 PRs, 147 pushes, 7 branches in 1 year 2 months
relativity
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.