
Results-driven Data Scientist with 8+ years of experience delivering machine learning and AI solutions for product and business optimization. Proven ability to design and scale end-to-end data science architectures from concept to production in cloud environments (Azure, Databricks). Skilled in Python, SQL, Spark, and statistical modeling with a strong foundation in mathematics and applied statistics.
Practical experience in transformer-based NLP, forecasting, and recommendation systems, including fine-tuning LLM models (BERT, DistilBERT). Adept at writing production-grade code and implementing ML pipelines using PySpark and MLflow. Passionate about leveraging data-driven methodologies to solve complex business problems.
Programming: Python, R, SQL, Scala
Machine Learning / Statistical Modeling / Analytics: classification, clusterization, regression, ranking, NLP, deep-learning (BERT, DistilBERT), recommendation systems, predictive modeling, hypothesis testing
Tools & Platforms: PySpark, Databricks, Azure Data Factory, MLflow, R Shiny, git, Google Data Studio, Jira
Cloud: Microsoft Azure
Visualization: Python (matplotlib, seaborn, Plotly), R Shiny, Google Data Studio
Publications & Projects
Developed R packages: DMR (2013), lmmfit (2011).