CV
About
- Name: Sem Sinchenko
- Title: Senior Data Engineer
- Company: Raiffeisenbank International AG
- Location: Belgrade, Serbia
- Key Skills: Python, Apache Spark, ETL, Scala, MLOps
- Languages:
- English
- Russian
Contacts
Career
Senior Data Engineer
- dates: July 2022 - onwards
- company: Raiffeisenbank International AG
- division: Advanced Analytics, Retail Tribe
- skills: Python, Databricks, PySpark, Apache Spark, MLFlow, SQL
Achievements:
- Designed and implemented ML Production Pipelines in Databricks with MLFlow and Apache Spark
- Created a lot of ETL-pipelines for various Data Marts with PySpark and Databricks
- Designed and implemented Feature Store for both Production and Development of ML Models
Data Engineer
- dates: October 2020 - July 2022
- company: Raiffeisenbank Russia
- division: HR Department
- skills: Python, Java, Scala, Apache Spark, Hadoop, Hive, Apache Airflow, SQL
Achievements:*
- Organized data of the whole department in Data Lake
- Organized data ingestion into Data Lake from various sources
- Created a lot of ELT-pipelines and Data Marts for BI reporting
- Organized migration of legacy Excel-based reports into Data Lake and Power BI
ML Engineer
- dates: January 2018 - October 2020
- company: Raiffeisenbank Russia
- division: Retail Marketing
- skills: Python, NumPy, SciPy, Tensorflow, Scikit-Learn, Pandas, PySpark, SQL
Achievements:
- Designer and implementer of machine learning models and processes
- Co-architect of the inner model-deployment Python library
- Creator of the massive-parallel implementations of few data science algorithms on top of the Apache Spark
Open Source Activities
Apache GraphAr (incubating) PMC
Achievements:
- Implemented Python API for the library for working with Graph Data in DataLakes
Education
MS, Solid State Physics
- dates: 2020 - 2022
- place: Moscow State University
Thesis: Probing a critical states of Heisenberg model with Artificial Deep Neural Network.
BS, Solid State Physics
- dates: 2011 - 2016
- place: Moscow Engineering Physics Institute
Thesis: Numeric modeling of X-Ray Powder Diffraction.
Self-education
Skills
Soft
- Agile
- Kanban
Common
- Computer Science
- Algorithms and Data Structures
Programming Languages
- Python
- Scala
- Java
Data Engineering
- Apache Airflow
- Apache Spark
- Pandas
- SQL
- DBT
- Apache Ni-Fi
- Deltalake
Machine Learning
- NumPy
- SciPy
- Scikit-learn
- Tensorflow
- Matplotlib
Achievements
Codewars
Hackathons
- Hackathon “Leaders of Digital 2020”, Russian Ministry of Energy use-case. Our team was placed 1st. The task was to create a end2end data process for prediction of an energy consumption. I was responsible for Machine Learning Back-end and data processing pipeline.