Michael Tuttle
Senior Engineer at Qualcomm
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolMichael Tuttle is an ML/AI engineer focused on model quantization and efficient on-device inference, bringing three years of industry and research experience to edge deployment challenges. Currently a Senior Engineer at Qualcomm after progressing from an engineer role there, he specializes in squeezing neural networks to run reliably on resource-constrained hardware. His contributions to the AIMET open-source library—implementing and testing batch norm folding and device-aware utilities for ONNX and PyTorch—reflect practical expertise in compression and optimization techniques used by production toolchains. Michael’s academic work at UIUC on microcontroller inference and earlier cybersecurity research at Cal Poly give him a rare mix of low-level systems understanding and ML model tooling. Based in San Diego, he combines hands-on engineering with a researcher’s attention to measurable efficiency gains for real-world embedded AI.
3 years of coding experience
5 years of employment as a software developer
California Polytechnic State University, San Luis ObispoMaster of Science - MS Electrical and Computer Engineering, Master of Science - MS Electrical and Computer Engineering at University of Illinois Urbana-Champaign
Github Skills (14)
net10
compression10
quantization10
pytorch10
machine-learning10
quants10
lossless-compression10
deep-learning10
onnx10
compress10
python9
deep-neural-networks9
neural-network9
open-source8
Programming languages (1)
Github contributions (3)
quic/aimet
Nov 2022 - Jan 2023
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Role in this project:
ML Engineer
ML EngineerContributions:172 reviews, 8 commits, 261 PRs in 1 month
Contributions summary:Michael primarily contributed to the AIMET repository, which focuses on quantization and compression techniques for neural networks. Their commits involve modifying and testing code related to batch norm folding and other optimization techniques within the ONNX and PyTorch frameworks. They implemented and tested features related to batch norm folding and fixed missing device arguments in utility functions.
pytorchtechniquesdeep-learningpruningcompression
quic-mtuttle/aimet
Nov 2022 - Mar 2025
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Contributions:19 pushes, 255 branches in 2 years 4 months
pytorchtechniquesdeep-learningcompressionmachine-learning
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.