Data Scientist (ML)

We are developing our own ML sales forecasting system for a large FMCG company.

The system is already running in production. Now we are developing internal expertise, improving existing models, and expanding the functionality of ML solutions.

We are looking for a Data Scientist who is interested in working on a real ML product: from data research and model development to their implementation and support in production.

• Development and implementation of ML models (the nearest project is time series forecasting)
• Exploratory Data Analysis (EDA)
• Experiments with various approaches and model algorithms
• Generation and verification of hypotheses to improve model quality. Maintaining and prioritizing a backlog of hypotheses
• Development of infrastructure for tracking experiments, automatic data updates, and model retraining
• Implementation (together with IT) of model results integration into target systems
• Visualization and interpretation of results for business units
• Documentation maintenance
• Participation in the development of internal ML tools and team best practices

• Data Scientist work experience of 2+ years;
• Experience in team development with a shared codebase in GitLab;
• Confident command of Python and essential libraries for data analysis, machine learning, and visualization: PySpark, pandas, NumPy, scikit-learn, Plotly;
• Practical experience in developing models and interpreting results based on gradient boosting: LightGBM, CatBoost, or XGBoost;
• Understanding of time series forecasting specifics: lag features, moving statistics, seasonality, temporal validation;
• Confident knowledge of SQL;
• Experience with DWH and object storage (S3);
• Understanding of how ML models work in production. Familiarity with MLOps practices;
• Experience with Airflow, Docker, and CI/CD
• English language at the level of reading technical documentation