Vladislav Devlikamov
Senior Machine Learning Engineer At Yandex Self-Driving Group
Nizhny Novgorod, Nizhny Novgorod Oblast, Russia
Summary
🤩
Rockstar🎓
Top SchoolVladislav Devlikamov is a Senior Machine Learning Engineer with 13 years of experience, currently building perception and ML systems at Yandex Self-Driving Group after roles at Yandex.Maps and YADRO. A Kaggle Notebooks Grandmaster, he blends research-grade graph techniques with practical ML engineering to ship high-performance solutions in production environments. He has hands-on experience optimizing GPU-accelerated computer vision code—contributing performance and refactoring improvements to the widely used OpenCV project. His background includes academic research on graph coarsening and applied genetics classification, reflecting a knack for translating theoretical methods into robust code. Based in Nizhny Novgorod, he pairs a strong computational mathematics education with a track record of speeding up core ML algorithms and improving maintainability in large codebases.
14 years of coding experience
6 years of employment as a software developer
Master's degree, Вычислительная и прикладная математика, Master's degree, Вычислительная и прикладная математика at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)
Github Skills (10)
cuda10
gpu-programming10
computer-vision10
opencv10
c-language10
cprogramming-language10
performance-optimization10
image-processing10
deeplearning-ai7
deep-learning7
Programming languages (6)
Github contributions (5)
opencv/opencv
Nov 2012 - Feb 2015
Open Source Computer Vision Library
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:7 commits, 66 PRs, 295 comments in 2 years 3 months
Contributions summary:Vladislav's contributions primarily involve optimizing and enhancing the OpenCV library's GPU-accelerated functionalities. They focused on modifying and adding element operations using CUDA, disabling performance tests for video processing components, and correcting compilation issues related to code refactoring. Additionally, they refactored and moved the device layer code to the core module, showcasing expertise in improving code structure and maintainability, likely to boost performance.
computer-visionc-plus-plusdeep-learningimage-processing
vinograd47/ctest-ext
Dec 2014 - Jul 2016
Contributions:6 releases, 48 commits, 8 PRs in 1 year 7 months
ctestctest-extension
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.