The Artificial Intelligence Development Department of the "B2C Transactional Banking" unit is looking for a professional for the Middle Data Scientist position. We are involved in the development and implementation of ML models on a huge B2C customer base to promptly offer clients credit card products, personalize service conditions, and automate customer support.
We are working on:
- Propensity and response models for SberBank Online and other distribution channels for card products.
- NLP models on text data (analysis of customer inquiries, chats, reviews to improve card products).
- Advanced approaches in classical ML: credit card limit management, uplift modeling for marketing campaigns, churn and grace period exit prediction, feature engineering on big data.
Responsibilities
- Build ML models based on various data: tabular, event sequences (card transactions, clickstream, operations), text.
- Write production-ready code and transfer it to the MLOps team's CI/CD pipeline (you are responsible for code quality and reproducibility).
- Improve the model building process, develop proprietary applied modules for the team's development framework to increase DS productivity and improve code quality in a production environment.
- Propose and justify the implementation of new ML models into the bank's processes, accompany the integration of models into lending and card servicing business processes.
- Generate data-driven hypotheses and proposals for launching new mechanics and card products, as well as find insights in the data.
Requirements
- Deep knowledge of classical ML and experience applying it to real business tasks (gradient boosting, NLP algorithms).
- Understanding of core Deep Learning approaches.
- Advanced SQL knowledge (window functions, query plan optimization).
- Excellent knowledge of Python, including libraries like lightgbm, pandas, numpy, sklearn, torch.
- Experience working with Hadoop, PySpark (query optimization, cluster-wide operation), Greenplum.
- Experience with credit and/or debit cards: understanding of lending business processes, scoring, limit management, offer personalization will be your advantage.
Conditions
- Comfortable modern office near Kutuzovskaya metro station.
- Hybrid work format.
- Annual salary review. Annual bonus.
- Corporate gym and recreation areas.
- Over 400 educational programs from SberUniversity for professional and career development.
- Adaptation program and manager support at the start.
- Extended voluntary medical insurance, preferential insurance for family, and corporate pension program.
- Flexible mortgage discount, equal to 1/3 of the Central Bank's key rate.
- Free Prime subscription with the possibility of sharing with three close contacts.
- Reward for recommending friends to the Sber team.
