Mikhail Surtsukov

Computer Vision Team Lead at Avride

Austin, Texas, 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
Mikhail Surtsukov is a Computer Vision Team Lead with 11 years of experience building perception systems for autonomous vehicles and delivery robots, currently leading scene recognition and an internal neural inference engine at Avride from Austin, TX. He previously led sensor-fusion multi-task perception work at Yandex Self-Driving Group, taking CV pipelines from research goals to efficient edge deployment. Deep learning-focused, he blends Bayesian DL and generative-model thinking with practical expertise in real-time, safety-critical systems, and has hands-on experience implementing Neural ODEs and VAE hybrids in PyTorch. A co-founder of a DL startup for hydraulic-fracturing analytics and an early robotics competitor, he combines entrepreneurial grit, research chops from MIPT, and a clear drive toward a driverless future.
code11 years of coding experience
job7 years of employment as a software developer
bookBachelor's degree, Information Technology, 4.54, Bachelor's degree, Information Technology, 4.54 at Moscow Institute of Physics and Technology (State University) (MIPT)
languagesEnglish, Russian
github-logo-circle

Github Skills (4)

jupyter-notebook10
python10
pytorch10
machine-learning9

Programming languages (2)

Jupyter NotebookPython

Github contributions (5)

github-logo-circle
msurtsukov/neural-ode

Jan 2019 - Apr 2019

Jupyter notebook with Pytorch implementation of Neural Ordinary Differential Equations
Role in this project:
userData Scientist
Contributions:20 commits, 2 PRs, 17 pushes in 3 months
Contributions summary:Mikhail primarily worked on implementing and adapting the Neural ODE model within a Jupyter Notebook. Their contributions involved initial setup and coding of the model, removing unused code and adding optional CUDA usage. The user also implemented the training of a VAE model using the neural ODE architecture and added spiral example visualization for the trained model.
jupyter-notebookneural-odepytorchvae
urtrial/gazebo_intro

Oct 2015 - Nov 2018

Contributions:1 PR, 26 pushes, 1 branch in 3 years
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
Mikhail Surtsukov - Computer Vision Team Lead at Avride