Jacob Szwejbka
Software Engineer 3 4 5 at Meta
Bellevue, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolJacob Szwejbka is a software engineer with six years of experience, currently advancing PyTorch's mobile runtime at Meta to bring efficient AI to phones and DSPs. He specializes in quantization and edge deployment, contributing significant features and optimizations to the high-profile pytorch/pytorch repo and improving the Executorch edge compiler. Jacob's background includes internships at Facebook and Lockheed Martin where he worked on data consistency and aerospace testbeds, reflecting strong systems and reliability instincts. Based in Bellevue and educated at UT Austin, he combines production-focused ML engineering with low-level runtime work, often surfacing subtle performance gains that matter on constrained devices.
6 years of coding experience
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at The University of Texas at Austin
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (10)
quantization10
pytorch10
machine-learning10
python9
tensor9
deep-learning8
c-language8
cprogramming-language8
gpu6
autograd6
Programming languages (4)
Github contributions (5)
pytorch/pytorch
Jan 2021 - Jan 2023
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:
ML Engineer
ML EngineerContributions:67 reviews, 78 commits, 113 PRs in 2 years
Contributions summary:Jacob primarily contributes to the PyTorch library, focusing on features related to quantization, specifically dynamic quantization. Their work involves adding new functionality for quantized tensors, refactoring and optimizing existing code for quantization, and creating and updating associated unit tests. They also worked on improving Executorch, which is a PyTorch edge compiler, adding support for dynamic quantization and implementing relevant backend configurations.
gpu-accelerationneural-networkpythonautogradgpu
JacobSzwejbka/executorch-1
Nov 2023 - Jul 2026
End-to-end solution for enabling on-device AI across mobile and edge devices for PyTorch models
Contributions:596 pushes, 178 branches in 2 years 8 months
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.