Nikolai Smolyanskiy
Director, Deep Learning For Perception And Prediction, Autonomous Vehicles at NVIDIA
Seattle, Washington, United States
Summary
👤
Senior🎓
Top SchoolNikolai Smolyanskiy is a seasoned leader in deep learning for perception and prediction, currently directing NVIDIA’s Machine Learning science team for autonomous vehicles with a focus on behavior prediction and multi-sensor perception. Over an 8+ year span at NVIDIA and prior roles at Microsoft Research and Hololens/Kinect, he has shipped DNNs for LiDAR/RADAR/camera perception, prediction networks used in NVIDIA Drive AV, and top-ranked stereo depth and visual odometry models on KITTI. He combines rigorous academic training (PhD in Applied Mathematics) with hands-on research-to-production experience across self-supervised, imitation, and reinforcement learning. Notably, his Redtail robotics work produced open-source models and SDK components that bridged autonomous drones/rovers research to practical robotics tooling. Based in Seattle, he blends long-term systems thinking with rapid prototyping, from immersive drone+VR prototypes to large-scale AV stacks.
8 years of coding experience
15 years of employment as a software developer
Master Degree, Applied Mathematics, diploma with honor, Master Degree, Applied Mathematics, diploma with honor at South Ural State University (SUSU)
Russian, English, French
Github Skills (5)
ros9
robotics9
perception7
reinforcement-learning1
ai-framework1
Github contributions (5)
nsmoly/redtail
May 2018 - May 2018
Contributions:3 commits, 4 PRs, 3 pushes in 1 day
roboticsautonomousreinforcement-learningai-frameworkros
nsmoly/BioloidController
Mar 2023 - Mar 2023
Contributions:6 commits, 4 pushes, 1 branch in 1 day
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.