A Data Scientist with over a year of experience. Winner of the hackathon "Digital Breakthrough" in 2023. I have skills working with Python, SQL, Docker, Git, Hadoop. My experience includes leading a 5-person development team, deploying recommendation systems and NLP models, and developing and implementing ETL processes using advanced technologies.
-
Data Analysis: Proficient in Python libraries, including NumPy, Pandas, and Scikit-learn.
-
Machine Learning: Experience with transformers (GPT, BERT), NLP, Linear Regression.
-
Databases: SQL, Experience with database integration for Telegram bots.
-
Data Visualization: Creating informative graphs and charts using Matplotlib and Plotly.
-
Team Lead | Startup Moscow, Russia | 12.2023 – Present
- Developed a startup project using Miro, Aris Express.
- Led a team of 5 people, assigning tasks in Trello, conducting code reviews.
- Developed a product MVP using Python (Aiogram3), PostgreSQL, Docker.
-
Data Scientist | RTU MIREA Moscow, Russia | 01.2023 – Present
- Speaker at 4 Data Science meetups (50+ attendees).
- Deployed the RecSys model in Jupyter Notebook.
- Developed two SQL databases (MySQL/PostgreSQL).
- Deployed NER (NLP) models Natasha (DeepPavlov) and SpaCy in Colab.
- Utilized machine learning models using scikit-learn, XGBoost, and CatBoost for various tasks.
- Worked with Hadoop (HDFS, YARN) and HBase NoSQL database.
-
Projects
-
LesMeh | 09.2022 – 05.2023
- Developed an asynchronous Telegram bot and Excel schedule parser.
- 860+ people using the bot, 300+ using it daily.
- Assembled a dataset for training the RuGPT-3 model.
- Running the bot in a Docker container. The bot works 24/7.
-
StudentGPT | 08.2023 – 10.2023
- Trained RuGPT-3 model on the LesMeh project dataset.
- Developed a telegram bot to test the model.
-
Feel free to reach out to me via email or connect with me on LinkedIn.