Master of Science with 2 years of international experience in natural language processing. Designed and deployed a variety of models using advanced AI/ML algorithms.
SKILLS
Natural language processing, Machine Learning, Neural Networks, Probability & Statistics
Python, SQL, Jupyter Notebook, VS Code, Docker
Teamwork: Agile, Kanban, Asana, Slack, Git
Python packages: numpy, pandas, spacy, nltk, sklearn, tensorflow, keras
EXPERIENCE
ROKO Labs
June, 2021 - current
- Data processing & analysis
- Building reports using Power BI
- Data clustering using ML Algorithms
Reputation Company, Kazan – Data Scientist
June 2019 - June 2021
- Built and optimized binary and multi-label models for sentiment and topic classification with accuracy up to 91%
- Conducted researches on natural language processing tasks: text segmentation, named entities recognition, phrases extraction, clustering and classification
- Scraped, parsed and prepared (text segmentation, cleaning and labelling) data for training machine learning models
- Deployed production models to generate responses based on sentiment and semantic of customer's reviews
Siemens, Kazan and Ilmenau - Scholar
September 2016 – August 2018
- Conducted researches on sensor data validation using ML algorithms (time series classification, clustering, visualization)
- Wrote and defended a master thesis on Sensor Data Validation under the company supervision
State Institute of Applied Optics, Kazan – Engineer
March 2016 – September 2017
- Designed documentation (circuit diagram, Bill-Of-Materials)
- Provided quality assurance of printed circuit boards and their components
- Wrote and defended bachelor thesis on PCB components placement under the company supervision
EDUCATION
TU Ilmenau, Ilmenau
Master of Science in Research in Computer & Systems Engineering
2016 – 2018
Kazan National Research Technical University – KAI, Kazan
Master of Science in Research in Computer & Systems Engineering
2016 – 2018
Kazan National Research Technical University – KAI, Kazan
Bachelor in Computer Science
2013 – 2016
CURRENT PROJECTS & RESEARCHES
Text segmentation into meaningful verb phrases
Multi-label classification research
Model training on very imbalanced data
INTERESTS
Personal Development
Data science blogging
Volunteer work to protect the environment
Moderate and participate in a book club
LANGUAGES
Russian (Native Speaker)
English (Upper-Intermediate)
German (Beginner)