Artem Borzov
Software Developer at СКБ Контур
Yekaterinburg, Sverdlovsk, Russia
Summary
👤
Senior🎓
Top SchoolArtem Borzov is a Software Developer based in Yekaterinburg with a decade of experience solving complex technical problems. He works at СКБ Контур since 2017, applying strong fundamentals from a degree in informatics and specialized training as a machine learning developer. Artem contributes to high-performance open-source ML infrastructure—notably enhancing CatBoost to support user-defined callbacks across Python and C++ cores, enabling custom training control and metric hooks. His work sits at the intersection of production-grade systems and ML tooling, balancing low-level C++ changes with Python usability. Colleagues rely on him for pragmatic refactors that make advanced model workflows observable and controllable. He combines academic rigor with hands-on engineering, quietly improving developer ergonomics in widely used ML libraries.
10 years of coding experience
Machine learning developer, Machine learning developer at Школа анализа данныхBachelor's degree, Fundamental informatics and information technology, Bachelor's degree, Fundamental informatics and information technology at Уральский Государственный Университет им. А.М. Горького
Английский, Russian
Github Skills (14)
callback10
machine-learning10
catboost10
c-language10
cprogramming-language10
python10
gradient-boosting10
data-science9
decision-tree9
gpgpu8
accelerated-computing8
gpu8
r5
kaggle5
Programming languages (9)
Github contributions (5)
catboost/catboost
Mar 2021 - May 2021
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
Role in this project:
ML Engineer
ML EngineerContributions:14 commits, 1 PR in 1 month
Contributions summary:Artem primarily focused on enhancing the CatBoost library's capabilities related to user-defined callbacks, a crucial aspect of machine learning model training. They implemented interfaces and functionalities for custom callbacks within the Python package and the core C++ code. The contributions included refactoring and adding new functionalities for handling the callbacks, ensuring the ability to intervene in the training process, enabling custom stopping criteria or metric logging. The changes involved modifications across Python and C++ code related to model training and integration.
kagglexgboostpythondata-mininglightgbm
urfu-2017/team3
Mar 2018 - Dec 2020
Contributions:79 PRs, 38 pushes, 1 branch in 2 years 9 months
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.