Nikita Selin
Machine Learning Engineer at Rutube
St Petersburg, St Petersburg City, Russia
Summary
🤩
Rockstar🎓
Top SchoolNikita Selin is a Machine Learning Engineer specializing in computer vision and NLP, with nine years of hands-on experience building and deploying ML systems across startups and product teams. Currently pursuing an MS in Applied Mathematics and Computer Science at ITMO University with a deep learning and generative AI focus, he combines academic rigor with practical engineering—optimizing inference with Triton and Milvus-backed embedding pipelines at Rutube and deploying FastAPI/Celery Docker services for production tracking at CyberCamera. His open-source work includes a high-quality neural background-removal tool that integrates U^2-Net and BASNet and demonstrates strong API and front-end integration skills. Comfortable moving research into production, he has delivered solutions from video QA metrics and embedding squeezing to real-time object tracking and segmentation. Outside ML, he studies Japanese and practices Wing Chun, reflecting a blend of disciplined curiosity and creative problem-solving.
8 years of coding experience
3 years of employment as a software developer
Master of Science - MS, Applied mathematics and computer science, Deep Learning and Generative Artificial Intelligence, Master of Science - MS, Applied mathematics and computer science, Deep Learning and Generative Artificial Intelligence at ITMO University
Github Skills (10)
neural-network10
computer-vision10
pytorch10
machine-learning10
tracer10
python10
dockers9
docker9
fastapi8
tensorflow8
Programming languages (5)
Github contributions (5)
OPHoperHPO/image-background-remove-tool
Jul 2019 - Jan 2023
✂️ Automated high-quality background removal framework for an image using neural networks. ✂️
Role in this project:
ML Engineer
ML EngineerContributions:13 releases, 14 reviews, 315 commits in 3 years 6 months
Contributions summary:Nikita primarily focused on implementing background removal functionality using neural networks. They initiated the project, added core files for the background removal tool, and then completely rewrote the codebase. Furthermore, they added support for new segmentation networks, including U^2-Net and BASNet, and integrated a trimap generator to refine the mask and improve image quality, demonstrating a focus on both model integration and performance enhancement. The user also refactored the API and added code for front-end integration.
mattingpythonbasnetremove-backgroundcomputer-vision
OPHoperHPO/hassio-addons
Aug 2019 - Jul 2022
:heavy_plus_sign: Docker add-ons for Hass.io
Contributions:64 commits, 52 pushes, 6 comments in 2 years 10 months
add-onssigndockerhassons
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.