Michael Boyarkin Email & Phone Number

Python, pandas, scikit-learn, SciPy, Matplotlib, Plotly, SQL, PostgreSQL, Greenplum, Apache Airflow, dbt, ClickHouse, Docker, Jira.Achievements:* Organized the transition of the digital marketing analytics of the customer company to a new architecture and infrastructure. The process became fast, scalable, systematic, template-driven, utilizing a flexible DWH based on DataVault 2.0Responsibilities:* Diving into and analyzing the business and its processes through data.*… Show more Python, pandas, scikit-learn, SciPy, Matplotlib, Plotly, SQL, PostgreSQL, Greenplum, Apache Airflow, dbt, ClickHouse, Docker, Jira.Achievements:* Organized the transition of the digital marketing analytics of the customer company to a new architecture and infrastructure. The process became fast, scalable, systematic, template-driven, utilizing a flexible DWH based on DataVault 2.0Responsibilities:* Diving into and analyzing the business and its processes through data.* Creating technical specifications and roadmaps/plans for testing and validating hypotheses to solve business problems.* Developing ETL (Extract, Transform, Load) processes and taking ownership on some of the projects.* Developing documentation and establishing data governance.* Creating highly presentable visualizations, including tables and charts.* Providing clean datasets to end users and modeling data.* Conducting code reviews of ETL logic (ad-hoc scripts, Airflow DAGs, dbt SQL models).* Building a Data Warehouse (DWH) following the DataVault 2.0 schema for a group of digital companies.* Creating analytical scenarios for data processing.* Conducting research and technological work.* Working with key metrics to measure various aspects of the business. Show less

* Conducted an in-depth analysis and developed a proposal for the expansion of the online clothing rental service, utilizing a model for estimating clothing sizes from photographs.* Developed a prototype service for detecting security incidents in large-scale DNS traffic analysis data. Stack: Python+aiohttp, Elasticsearch.

* Developed a model and visualization for the aluminum production stabilization system, resulting in a 20% reduction in chemical components. Resolved the issue of numerous hypotheses by selecting a promising one and assisting in its successful implementation.* Prevented the risks of paying out million-dollar penalties for the delivery of substandard products by stabilizing key quality parameters of nitrate fertilizers through a raw material chemical composition forecasting system.*… Show more * Developed a model and visualization for the aluminum production stabilization system, resulting in a 20% reduction in chemical components. Resolved the issue of numerous hypotheses by selecting a promising one and assisting in its successful implementation.* Prevented the risks of paying out million-dollar penalties for the delivery of substandard products by stabilizing key quality parameters of nitrate fertilizers through a raw material chemical composition forecasting system.* Ensured the availability of a training dataset (tens of terabytes) for creating one of the large neural networks for generating images based on text prompts (ruDALL-E). Stack: PyTorch, TensorFlow, MLCloud, GPU+Docker. Show less

* Established the creation of a high-performance service for processing and analyzing logs of the mail service. The system is capable of incident detection within tens of millions of emails while processing up to 1,000 emails per second within a few minutes.* Participated in the development of a surgical navigation system using spatial cameras and augmented reality technologies. Stack: C++, OpenCV, ITK, CMake, C#, Unity.* Involved in the productization of a service for scientific… Show more * Established the creation of a high-performance service for processing and analyzing logs of the mail service. The system is capable of incident detection within tens of millions of emails while processing up to 1,000 emails per second within a few minutes.* Participated in the development of a surgical navigation system using spatial cameras and augmented reality technologies. Stack: C++, OpenCV, ITK, CMake, C#, Unity.* Involved in the productization of a service for scientific analysis of rocks computer tomography. Stack: Python+FastAPI, MongoDB, TypeScript, Azure DevOps. Show less

* Developed a system for analyzing the techno-economic indicators of a thermal power plant, and I created a fuel consumption optimization system for the thermal power plant. This system has shown proven economic benefits and is operational in 25% of power generation companies in Russia (C# + MS SQL Server/Oracle).* Additionally, I introduced and managed Agile methodologies within the company, facilitating regular releases and the rapid distribution of the product (Scrum, Kanban, MS TFS).

* Development of algorithms for clustering and indexing of complex graphical information. * Development of algorithms for segmentation of human faces and human skin in images. * Data analysis, preparation of visualizations and scientific reports (MATLAB, Oracle, C++).* Defended thesis for the degree of PhD in Technical Sciences

* Enterprise development of multidimensional data processing software for automatic generation of complex reports for the energy industry (custom in-house developed OLAP based on Oracle Database).* Development of Web application for reports generation. C# (ASP.Net) + Oracle.

Development of industrial control data processing system

Doctor Of Philosophy - Phd, System Analysis, Management, And Information Processing In Industry., Phd In Technical Sciences

Activities and Societies: Candidate's thesis: Synthesis of information system for grouping multiple data with cluster analysis.

Applied Mathematician, System Programmer., Master Degree

Graduated with Honors.