Description
We are looking for an ML Engineer to join the team of the Public Sector Department within the Corporate and Investment Banking block of the bank. The Corporate and Investment Banking block is responsible for working with legal entities and individual entrepreneurs, from micro-businesses to the largest corporations. Key areas include the development of Sberbank Group ecosystem products, banking services (loans, current accounts, deposits, etc.), as well as analytical services and legal support for businesses.
Our team works with structures representing various levels of government management, as well as enterprises and organizations established by them (hereinafter referred to as DRGS, the Department for Work with the Public Sector).
Responsibilities
- collecting, structuring, analyzing, and preparing data for machine learning
- building industrial recommendation systems for selling ecosystem and bank products, integrating them into the bank's end-to-end business processes
- forecasting churn by products, volumes, and activity of product/service usage
- analyzing companies' transactional activity and related time series
- creating and developing ML models that will help our traders make fast and accurate decisions based on large volumes of data
- defending ML models during internal bank validation
- monitoring ML models in operation, analyzing deviations in quality metrics
- fine-tuning ML models
- creating AI agents and RAG systems
- prompt-tuning, additional training, implementation of ML models based on LLM
- interacting with business clients and other specialists within the scope of assigned tasks.
Requirements
- higher education (Master's degree) in Data Science, Computer Science, Statistics, Mathematics, Econometrics, or related disciplines
- at least 1 year of work experience in the field of Data Science
- programming: Python (required: pandas, scikit-learn, NumPy, SciPy); SQL (working with relational databases)
- ML/AI: knowledge of modern frameworks: PyTorch, TensorFlow, Keras; experience in building and implementing models: classification, regression, clustering, ranking, forecasting, NLP; experience in applying rule-based and template-based methods for extracting structured data from known document formats
- experience working with big data (Hadoop, Spark)
- instrumental proficiency in AI for analysis, generation, and automation
Will be a plus:
- experience in bank sales campaigns
- knowledge of PySpark, features of writing code for the Hadoop stack
- experience in applying LLMs;
- certificates, prize places in hackathons, high rankings in AI competition tasks.
Conditions
- comfortable modern office
- corporate gym and recreation areas
- more than 400 educational programs from SberUniversity for professional and career development
- adaptation program and manager assistance at the start
- extended voluntary health insurance, preferential insurance for family, and corporate pension program
- free SberPrime+ subscription, discounts on products from partner companies
