Yathindra Kota
Staff Software Engineer at Qualcomm
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolYathindra Kota is a Staff Software Engineer based in the San Francisco Bay Area with four years of professional experience and an M.S. in Computer Engineering from the University of Florida. He currently drives engineering work at Qualcomm, focusing on performance-conscious software for complex systems. As an active contributor to AIMET, he has enhanced quantization and compression features for neural network models—adding QuantizationDataType support, float quantization for tensor quantizers, QAT tests, and Spatial SVD examples—demonstrating practical ML optimization expertise. Yathindra blends low-level systems thinking from an electrical and electronics engineering background with hands-on ML tooling improvements, making him adept at turning research-grade techniques into production-ready optimizations.
4 years of coding experience
Bachelor of Engineering (B.E.), Electrical and Electronics Engineering, Bachelor of Engineering (B.E.), Electrical and Electronics Engineering at PES institute of technology , BangaloreMaster of Science (M.S.), Computer Engineering, Master of Science (M.S.), Computer Engineering at University of Florida
Telugu, Kannada, German, English
Github Skills (12)
net10
compression10
quantization10
pytorch10
machine-learning10
quants10
lossless-compression10
deep-learning10
model-optimization10
compress10
python9
tensorflow9
Programming languages (1)
Github contributions (3)
quic/aimet
Oct 2021 - Oct 2022
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Role in this project:
ML Engineer
ML EngineerContributions:18 reviews, 34 commits, 123 PRs in 1 year
Contributions summary:Yathindra contributed significantly to the AIMET library, focusing on enhancing its quantization and compression capabilities for neural network models. Their work involved modifying comments and adding support for QuantizationDataType, including the implementation of float quantization for tensor quantizers. Key contributions include adding QAT tests, refining fp16 handling, and adding encoding support, demonstrating a strong focus on improving the library's functionalities related to model optimization. The user also added the initial support for the Spatial SVD example.
pytorchtechniquesdeep-learningpruningcompression
quic-ykota/aimet
Sep 2021 - Feb 2025
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Contributions:4 pushes, 122 branches in 3 years 5 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.