I am a Senior Data Scientist and Machine Learning Engineer with over seven years of experience developing production machine learning systems across ad tech, retail, industrial optimization, and telecommunications.
I specialize in ranking and recommendation systems, classification and regression, uplift modeling, predictive optimization, and experimentation. My work has delivered measurable business outcomes, including CPM uplift for advertising traffic, improved out-of-stock prediction, and increased industrial throughput and recovery.
I build end-to-end ML solutions, from data preparation and feature engineering to offline evaluation, deployment, monitoring, and iterative improvement. I have experience working with large-scale datasets, including hundreds of millions of sensor records and millions of daily traffic slices.
My technical background includes Python, SQL, gradient boosting, deep learning, factorization machines, and reinforcement-learning-related approaches such as multi-armed bandits. I use PyTorch, scikit-learn, Vowpal Wabbit, and distributed data-processing tools to develop reliable models.
I am experienced in MLOps and production observability, including Airflow orchestration, Docker, MLflow, CI/CD, data-quality validation, and monitoring with Grafana and VictoriaMetrics. I focus on creating measurable, maintainable ML systems that support real-world decision-making.
I hold a Specialist Degree in Mathematics, equivalent to a Master's degree, from Lomonosov Moscow State University. My mathematical foundation supports my work in machine learning, probability, optimization, and data-driven product development.
