Michael Klachko

Principal ML Engineer at EnCharge AI

Santa Barbara, California, United States
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

👤
Senior
🎓
Top School
Michael Klachko is a Principal ML Engineer with 11 years of experience building and deploying deep learning systems across computer vision, speech, music generation, and large language/diffusion models. He combines a PhD in mixed-signal, ultra-low-power hardware accelerators with hands-on expertise in model compression (quantization, pruning, matrix factorization) and squeezing accuracy/performance under chip area, power and noise constraints. At EnCharge AI he designs quantization algorithms and maintains QAT/PTQ infrastructure and a model zoo for hardware deployment, after driving hardware-aware benchmarking and co-design at Luminous Computing and novel quantization patents at Mythic. Equally comfortable in TensorFlow and PyTorch, he is transitioning to JAX while applying research-grade methods to production accelerators. Based in Santa Barbara, he brings a rare blend of systems-level hardware insight and production ML tooling that accelerates model delivery on constrained silicon.
code11 years of coding experience
job12 years of employment as a software developer
bookDoctor of Philosophy (Ph.D.), Computer Engineering, Doctor of Philosophy (Ph.D.), Computer Engineering at University of California, Santa Barbara
languagesEnglish, Russian
github-logo-circle

Github Skills (200)

python10
expressions10
language-server-protocol10
deep-learning10
gpu10
gpu-acceleration10
noise10
cudnn10
efficientnet10
python-development10
qt10
acceleration10
optimizer10
numpy10
resnet10

Programming languages (9)

TypeScriptC++CScalaJavaScriptGoHTMLJupyter Notebook

Github contributions (5)

github-logo-circle
michaelklachko/pnn.pytorch

Aug 2018 - Oct 2018

PyTorch implementation of CVPR'18 - Perturbative Neural Networks http://xujuefei.com/pnn.html
Contributions:36 commits, 30 pushes in 1 month
pytorchloss-functionsneural-networkspnnpytorch-implementation
michaelklachko/NoisyNet

Apr 2019 - Feb 2022

Code for "Improving Noise Tolerance of Mixed-Signal Neural Networks" https://arxiv.org/abs/1904.01705
Contributions:108 commits, 1 PR, 104 pushes in 2 years 10 months
pytorchsignalmixed-signalarxivabs
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
Michael Klachko - Principal ML Engineer at EnCharge AI