Andrew Selle
Software Engineer at Apple
Los Altos, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAndrew Selle is a senior software engineer with 15 years of experience building production-grade ML infrastructure and high-performance simulation systems, currently advancing on-device ML at Apple after shaping TensorFlow and TensorFlow Lite at Google. He blends deep research credentials (PhD-level work and published SIGGRAPH simulation research) with hands-on production engineering—leading mobile runtimes, MLIR-based compilers, and edge inference used on billions of devices. His earlier career built physically realistic simulation and rendering systems for Walt Disney Animation and ILM, including open-source tools like the Partio particle library and a published MPM snow simulator. Equally comfortable in C++, Python, and systems-level design, he has a track record of reducing research-to-production friction by unifying runtimes, APIs, and tooling. Based in Los Altos, he pairs studio-scale visual effects expertise with cutting-edge ML infra—an unusual combination that fuels practical, performant systems for both film and mobile AI.
15 years of coding experience
18 years of employment as a software developer
BS Computer Science Mathematics, BS Computer Science Mathematics at University of Wisconsin-MadisonAS Research and Development Machinist, AS Research and Development Machinist at DeAnza CollegePhD Computer Science, PhD Computer Science at Stanford University
Stackoverflow
51reputation
14kreached
1answer
0questions
Github Skills (3)
cprogramming-language10
c-language10
particle10
Programming languages (7)
Github contributions (5)
wdas/partio
Jul 2010 - Apr 2016
C++ (with python bindings) library for easily reading/writing/manipulating common animation particle formats such as PDB, BGEO, PTC. https://wdas.github.io/partio
Role in this project:
Back-end Developer
Back-end DeveloperContributions:81 commits, 12 PRs, 9 pushes in 5 years 10 months
Contributions summary:Andrew contributed to the `wdas/partio` repository by adding functionality for reading and writing particle data in the prman unordered PointCloud format. Their work involved implementing a reader and writer for this format within the existing C++ library. This addition expanded the library's support for handling various animation particle formats, aligning with the project's purpose of facilitating the manipulation of particle data. Further contributions included adding PDB file read/write support.
groupsparticleanimationpythoncpp
aselle/tensorflow
Aug 2016 - Feb 2019
Computation using data flow graphs for scalable machine learning
Contributions:50 commits, 64 pushes, 76 branches in 2 years 6 months
computationscalabledata-sciencemachine-learninggraphs
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.