I am a data scientist with 5 years of industry experience specializing in machine learning, statistical analysis, and ML deployment. My expertise spans working with tabular data, deep learning, and collaborating effectively with cross-functional teams. I am passionate about leveraging data to solve complex problems and drive impactful business decisions.
Currently, I am expanding my skills in MLOps and scalable infrastructure to enhance the deployment and maintenance of machine learning models in production environments. I have hands-on experience in developing computer vision models, natural language processing, and classical machine learning techniques.
Throughout my career, I have contributed to various projects including building transformer-based UNet architectures for image segmentation, automating technical documentation workflows, and developing recommender systems. I am proficient in Python and SQL, and familiar with a wide range of libraries and tools such as pandas, scikit-learn, PyTorch, FastAPI, and Docker.
I am a proactive learner and continuously seek to improve my technical skills and domain knowledge. My background includes working with large-scale SQL analytics, feature engineering, and exploratory data analysis. I am comfortable working in agile environments and collaborating with domain experts to deliver high-quality solutions.
I am fluent in Russian and English, with beginner proficiency in Finnish. I am open to relocation and eager to contribute to innovative projects that challenge my abilities and foster professional growth.
– Led an end-to-end computer vision model development using transformer-based UNet architecture for segmentation of microscopic images.
– Contributed to the data annotation and curation processes by labeling medical image data and led iterative model development through collaboration with domain experts.
– Built internal automation tools for technical documentation workflows using Python, Docker, and Docusaurus.
– Developed Dash-based dashboards for visualization and monitoring internal resource usage across software components.
– Developed CatBoost models to automatically resolve OCR output conflicts, reducing manual review by 87%.
– Performed data preparation, curation and analysis by querying large datasets from PostgreSQL and ClickHouse databases.
– Built automated data preparation workflows by extracting, cleaning, and standardizing features from natural language data.
– Prototyped cost prediction ML models, demonstrating initial experience in developing AI/ML solutions.
Jobicy
578 professionals pay to access exclusive and experimental features on Jobicy
Free
USD $0/month
For people just getting started
Plus
USD $8/month
Everything in Free, and: