The work
- Develop and deploy classic ML models, including boosting, logistic regression, random forests and linear models.
- Work on credit scoring, churn prediction, risk assessment, collaborative-filtering recommendations and time-series forecasting.
- Create and select features from structured data using SQL, Spark or Pandas.
- Build training and validation pipelines with interpretability methods such as SHAP, LIME and feature importance.
- Build A/B testing and post-release monitoring pipelines for data and target drift.
- Integrate models through APIs and container orchestration.
- Agree business metrics with customers, present results and write technical documentation.
Role-specific skills
- Commercial Data Science or ML development experience.
- Strong Python skills with pandas, NumPy, scikit-learn and a boosting framework such as LightGBM, XGBoost or CatBoost.
- Confident SQL skills with databases such as ClickHouse, PostgreSQL or Greenplum.
- Understanding of classification, regression and ranking metrics.
- Experience building ML pipelines from data extraction to deployment and monitoring.
- Knowledge of MLflow, DVC and CI/CD for ML projects.
Commercial experience
We consider Junior+, Middle and Senior specialists. Each field requires at least six months of relevant commercial experience. Courses and personal projects can add to it.
Courses and personal projects do not replace commercial experience.
Experience using AI tools in commercial work is a plus, with results checked through tests and review and confidentiality respected.
Tell us about your experience
Tell us about an ML problem and its target metric. Describe features, validation, model interpretation and your integration or monitoring experience.
Share your experienceWe connect with specialists in this field for future projects. This page is a role profile, not an open vacancy.