Hitarth Mehta
Staff Software Engineer at Qualcomm
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHitarth Mehta is a Staff Software Engineer based in San Diego with 8+ years at Qualcomm focused on neural network compression, quantization, and LLM-related tooling for hardware deployment. He progressed from deep learning research engineer to staff-level technical lead, shipping production-ready quantization features that bridge model research and efficient inference on Qualcomm silicon. An active contributor to AIMET, he implemented multi-input data subsampling and parameter-encoding utilities that strengthen post-training quantization workflows and test coverage. Hitarth combines an MS in Computer Engineering with hands-on experience in both simulation-driven research and large-scale ML engineering, bringing a rare blend of low-level systems thinking and practical ML model optimization.
6 years of coding experience
5 years of employment as a software developer
BE, Electronics and Communication Engineering, BE, Electronics and Communication Engineering at L.D College of Engineering - AhmedabadMS, Computer Engineering, MS, Computer Engineering at University of Florida
Github Skills (10)
compression10
quantization10
pytorch10
machine-learning10
lossless-compression10
deep-learning10
tensorflow10
compress10
python9
open-source8
Programming languages (2)
Github contributions (3)
quic/aimet
May 2020 - 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:192 reviews, 92 commits, 349 PRs in 2 years 8 months
Contributions summary:Hitarth contributed significantly to the AIMET library, focusing on enhancements related to quantization and data handling within the context of deep learning models. They added support for multiple inputs in data subsampling, demonstrating a good understanding of data preprocessing pipelines. Furthermore, they implemented new features for setting and freezing parameter encodings, which is crucial for post-training quantization workflows. The user's work involves modifying test files and implementing utilities related to the quantizer, implying they are involved with development and testing of quantization features.
pytorchtechniquesdeep-learningpruningcompression
quic-hitameht/aimet
May 2020 - Mar 2025
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Contributions:4 pushes, 309 branches in 4 years 11 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.