Kirill Mishchenko - Team Lead at Yandex

Kirill Mishchenko

Team Lead at Yandex

Russia

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Kirill Mishchenko is a Team Lead with 9 years of experience delivering machine-learning features and search infrastructure at Yandex, currently focusing on ML capabilities for Yandex Browser. He has a strong backend and ML engineering background, having led search suggest and goods search teams and shipped production systems across search and assistant products. An active open-source contributor, Kirill has contributed algorithmic work to prominent C++ ML libraries like mlpack and performance optimizations to CatBoost, including Softmax Regression, cross-validation tooling and Numba-accelerated custom metrics. He combines research-rooted training from Ural Federal University and Yandex School of Data Analysis with hands-on system design, testing and metric-driven evaluation. Known for refactoring and adding cleaner interfaces (e.g., Classify vs Predict, LARS beta access), he brings both code-quality discipline and practical performance improvements to production ML stacks. Based in Russia, he blends academic rigor with product-focused leadership across large-scale search and ML engineering challenges.

9 years of coding experience

6 years of employment as a software developer

Computer Science, Computer Science at Yandex School of Data Analysis

Researcher, Computer Science, Researcher, Computer Science at Уральский федеральный университет / Ural federal university

Github Skills (29)

c-language10

python10

machine-learning10

numpy10

gradient-boosting10

regression10

cython10

numba10

cprogramming-language10

optimization10

data-structure9

software-design9

categories9

algorithm9

algorithms9

Programming languages (1)

C++

Github contributions (5)

mlpack/mlpack

Mar 2017 - Sep 2017

mlpack: a fast, header-only C++ machine learning library

Role in this project:

Back-end Developer & ML Engineer

Contributions:3 reviews, 162 commits, 17 PRs in 5 months

Contributions summary:Kirill primarily contributed to the implementation of the Softmax Regression method within the mlpack library. Their work involved adding and modifying methods related to classification, specifically introducing the `Classify` method and refactoring the existing `Predict` method. The user also updated references within the code, ensuring that the new `Classify` method was correctly utilized throughout the codebase. Furthermore, they introduced the training constructors to LARS and the new interface for accessing the Beta from the LARS model.

regressionheaderdeep-learningscientific-computingc-plus-plus

mlpack/ensmallen

May 2017 - Sep 2017

A header-only C++ library for numerical optimization --

Role in this project:

ML Engineer

Contributions:33 commits in 3 months

Contributions summary:Kirill contributed to the cross-validation module, adding metrics like accuracy, mean squared error, precision, recall, and F1 score. These changes involved integrating existing machine-learning models and testing frameworks within the `mlpack` library. The commits demonstrate an understanding of model evaluation and metrics relevant to machine-learning model performance, with a focus on the testing of these functionalities.

optimization-methodsoptimization-algorithmsnumerical-optimizationheader-onlycplusplus

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.

Request Free Trial