Description
The "Segments" team is a team specializing in creating ML models for analyzing customer churn, reducing transactional activity, and identifying propensities for various products. We strive to find the best solutions for the business. Our team consists of six people, including graduates from prestigious universities such as Moscow State University and HSE.
The vacant position is a cross-functional role combining tasks of business analytics, model building, and their industrial implementation to achieve ambitious goals.
Responsibilities
- Development and training of models for predicting customer behavior to recommend the most relevant options and services
- Analysis of various data types (tabular data, transactional data, logs, graphs, and others) to find patterns, root causes, and insights
- Automatic generation of hypotheses for customer retention and development
- Participation in the development and validation of business and technical hypotheses
- Creation of industrial versions of models and participation in their integration into platforms
- Assessment of business effects of implemented solutions
- Development and optimization of ETL pipelines for processing large volumes of data
- Industrial implementation of ML models.
Requirements
- Deep knowledge and practical experience in applying classical machine learning (ML) methods and programming in Python
- Basic understanding of deep neural networks and the possibility of their use for solving business problems, especially on tabular data
- Skills in evaluating model result quality from both Data Science and business needs perspectives
- Advanced knowledge in the field of statistics and conducting A/B tests
- Experience working with GreenPlum, PostgreSQL databases, as well as Spark and PySpark frameworks
- Confident knowledge of the main components of the Apache Hadoop ecosystem and experience with Apache Spark
- Advanced knowledge of SQL and Python; experience in industrial development and implementation of solutions for 1+ years
- Experience with Python ML frameworks (Scikit-Learn, LightGBM, PyTorch, and others)
- Experience with Spark Streaming, Kafka, HBase, GreenPlum
- Experience with DevOps tools (Jenkins), Git (BitBucket)
- Experience working with Agile methodology (SCRUM, Kanban).
Will be a plus:
- Experience in developing solutions using GenAI
- Experience in business analytics and leading DS-projects
- Knowledge of Scala.
Conditions
- Comfortable modern office near Kutuzovskaya metro station
- Work format - office
- Annual salary review, annual bonus
- Corporate gym and relaxation areas
- More than 400 educational programs from SberUniversity for professional and career development
- Extended DMS, preferential insurance for family and corporate pension program
- Flexible mortgage discount equal to 1/3 of the Central Bank's key rate
- Free SberPrime+ subscription, discounts on products from partner companies
- Referral bonus for recommending friends to the Sber team.
