Mayflower is a technology company building highload products used by millions of people worldwide. Operating at the scale of one of the world's top-50 websites, we solve complex engineering challenges and create solutions that power real-time entertainment for a global audience.
Now we look for a Data Scientist to join our ML team
• Develop and train machine learning models for prediction, classification.
• Build and evaluate regression, classification, clustering, and time-series models.
• Design feature engineering pipelines and data preprocessing workflows.
• Evaluate model performance, robustness, and production readiness.
• Deploy and maintain ML models in collaboration with ml-ops teams.
• Explore large datasets to identify patterns, trends, and hidden relationships.
• Perform statistical analysis and hypothesis testing.
• Distillate open-source datasets by proprietary data via LLM agents
• Detect anomalies, outliers, and unexpected metric movements.
• Translate business or product questions into analytical tasks.
• Work with data pipelines and streaming data systems.
• Process and transform large datasets using Python and SQL.
• Work with event streams and messaging systems (Kafka).
• Contribute to data quality monitoring and dataset validation.
• Work with analytical databases and data warehouses.
• Design experiments and evaluate model performance in real environments.
• Implement monitoring for model performance and data drift.
• Support A/B testing and experimentation frameworks.
• Improve models based on production feedback and metrics.
• Work closely with ML engineers, data engineers, and product teams.
• Communicate model results and analytical insights clearly.
• Contribute to the development of ML best practices within the team.
• Strong Python programming skills for data science and machine learning.
• Experience working in Jupyter / Python notebooks for experimentation and analysis.
• Strong experience with pandas and numerical data processing.
• Experience with SQL databases and complex analytical queries.
• Experience working with ClickHouse or other analytical columnar databases.
• Experience working with Kafka or other streaming data platforms.
• Experience building and evaluating machine learning models using libraries such as scikit‑learn, XGBoost, LightGBM, or similar.
• Understanding of statistics, probability, and experimental design.
• Experience working with large datasets and data preprocessing pipelines.
Nice to Have
• Experience with deep learning frameworks (PyTorch or TensorFlow).
• Experience deploying ML models to production environments.
• Experience working with Computer Vision models (OpenCV, CNNs, object detection frameworks).
• Experience with distributed data processing or large-scale ML systems.
• Familiarity with ML monitoring, experiment tracking, and model versioning tools.
We know that great talent deserves great conditions, so here's what you can expect when joining us: