Alexey Prutskov
Senior Machine Learning Engineer at Sberbank
Nizhny Novgorod, Nizhny Novgorod Oblast, Russia
Summary
🤩
Rockstar🎓
Top SchoolAlexey Prutskov is a Senior Machine Learning Engineer with nine years of experience building high-performance ML systems and recommendation platforms, currently driving AI agent and personalized search initiatives at Sberbank. He combines production-focused ML engineering—deploying real-time microservices with Kubernetes, FastAPI, Spark, MLflow and Seldon—with low-level optimization experience from Intel, where he improved oneDAL algorithms and contributed to Modin’s distributed pandas. Alexey has led teams as a tech lead, cutting infrastructure costs by 38% and standardizing CI/CD and GitFlow across recommendation projects for multiple products. His open-source contributions include implementing pandas-aligned datetime and shift operations in Modin and developing unidist, reflecting a rare blend of distributed data-processing expertise and hands-on GPU/heterogeneous computing optimization. Notably, he bridges research and productization, turning prototypes into scalable, cost-efficient systems used across consumer-facing services.
9 years of coding experience
6 years of employment as a software developer
Master's degree, Information systems and technologies, Master's degree, Information systems and technologies at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)
Github Skills (18)
datetime10
date-manipulation10
back-end-development10
python10
dataframes10
pandas10
machine-learning10
machine-learning-algorithms10
datetimes10
dataframe10
linear-regression10
oneapi10
gpu10
datetime-format10
cpp10
Programming languages (3)
Github contributions (5)
modin-project/modin
May 2020 - Aug 2022
Modin: Scale your Pandas workflows by changing a single line of code
Role in this project:
Back-end Developer
Back-end DeveloperContributions:785 reviews, 93 commits, 83 PRs in 2 years 3 months
Contributions summary:Alexey primarily contributed to implementing the `dt` property for the `Series` class in the Modin library, which involved adding methods and properties related to datetime functionality. They introduced the `shift` function for both `Series` and `DataFrame` objects, and also implemented the `nsmallest` and `slice_shift` functions. The contributions involved modifying core Modin code, adding new functionality, and updating existing implementations to align with pandas features.
analyticspythonline-of-codedata-sciencedataframe
uxlfoundation/oneDAL
Oct 2019 - Feb 2020
oneAPI Data Analytics Library (oneDAL)
Role in this project:ML Engineer
ML EngineerContributions:3 reviews, 11 commits, 19 PRs in 4 months
Contributions summary:Alexey contributed to the oneDAL library, focusing on machine learning algorithms. Their work included adding instrumentation tasks using Intel's ITT Notify for Linear Regression training, enhancing the code for GPU acceleration, and integrating block size optimization for GEMM/SYRK stages. Furthermore, the user implemented and integrated Linear Regression in online mode, including algorithm development, example code, and fixes to the prediction kernel. This points to a strong involvement in developing and optimizing ML algorithms within a high-performance computing context.
swrepodata-analyticsanalyticscppdata-analysis
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.