Ali Hadizadeh

Co-Founder, Lead Scientist at ByteShape

Old Toronto, Ontario, Canada
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Ali Hadizadeh is a co-founder and lead scientist who builds practical tools to accelerate deep learning, specializing in automated quantization and compression for LLMs and generative models. With a PhD from the University of Toronto and seven years of hands-on experience across academia and industry, he pioneered GOBO and its successor Mokey—early post-training quantization methods that shrink transformers without fine-tuning. He has driven system-level engineering at 1QBit and Irreversible, pairing algorithmic innovation with hardware-aware designs to cut memory traffic and energy for inference and training. Based in Toronto, he blends research rigor with startup execution, routinely translating paper ideas into deployable accelerators and model optimization toolchains. An uncommon strength is his end-to-end focus: from mathematical quantization techniques to FPGA and memory-compression implementations that maximize on-chip efficiency.
code7 years of coding experience
job9 years of employment as a software developer
bookDoctor of Philosophy - PhD, Computer Engineering, 4/4, Doctor of Philosophy - PhD, Computer Engineering, 4/4 at University of Toronto
bookMaster of Science - MS, Digital Systems, Electrical Engineering, 4/4, Master of Science - MS, Digital Systems, Electrical Engineering, 4/4 at Sharif University of Technology
languagesEnglish, Persian
github-logo-circle

Github Skills (16)

transformers10
gemma10
audio10
transformer10
machine-learning10
pytorch10
speech-recognition10
nlp10
inference10
deep-learning10
multimodal10
python10
machine-learning-models10
natural-language-processing10
glm10

Programming languages (2)

C++Python

Github contributions (4)

github-logo-circle
aps1070-2019/datasets

May 2020 - Feb 2022

Contributions:26 pushes in 1 year 9 months
huggingface/transformers

May 2020 - Sep 2021

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Contributions:2 reviews, 3 comments, 2 issues in 1 year 3 months
audioinferencemachine-learning-modelsmultimodaltransformers
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.
Request Free Trial