Description
We are looking for a colleague to join the Portfolio Risk Modeling Center.
You will work in a large and well-organized team of professionals and develop models with a significant impact on the Bank's P&L.
You will get a unique chance to immerse yourself in retail credit processes and portfolio modeling, becoming a professional in this field.
You will participate in interactions with many teams: data engineers, developers, methodologies, and analysts.
Responsibilities
- building models for various tasks (classical ML: macroeconomic forecasting models, reserves and retail loan portfolio metrics + AI agents for automatic portfolio monitoring)
- analysis of business processes and formulation of model development tasks together with the customer and colleagues
- selection of suitable architectures and model solutions
- interaction with DE during data collection
- monitoring of models in production, analysis of deviations
- development and dissemination of expertise during model implementation (consultation on factors/algorithms, formulation of technical specifications for implementation, analytics)
- mentoring interns.
Requirements
- higher education in technical/physical-mathematical sciences (preferably from MIPT, Moscow State University, Novosibirsk State University, MEPhI, HSE, ITMO)
- knowledge of mathematical foundations of classical machine learning and neural networks
- knowledge of algorithms and data structures
- knowledge of Python and data analysis libraries: PyTorch, HuggingFace and Transformers
- knowledge of SQL, experience working with databases
- understanding of the principles of design, training, and quality evaluation of large language models (LLM)
- model development experience of at least 2 years
- skills in working with generative AI models; experience in creating AI agents and using them in work will be an advantage
- experience using GigaChat, Kandinsky and similar tools in products, skills in creating and using AI agents
- instrumental proficiency in AI for analysis, generation, and automation.
Will be a plus:
- understanding of key credit risk metrics, components of bank product profitability and experience working with them
- understanding of retail banking products, processes, and unit economics (annuities, revolving, tranche)
- knowledge of statistical analysis
- experience with LLM and RAG (LangChain/GigaChain, LangGraph)
- experience implementing long-term projects
- knowledge of PySpark.
Conditions
- fixed-term employment contract until July 2027
- comfortable modern office near Kutuzovskaya metro station
- work format: full-time office
- annual bonus
- corporate gym and relaxation areas
- more than 400 educational programs from SberUniversity for professional and career development
- regular meetups and a well-developed DS community
- extended VHI, preferential insurance for family and corporate pension program
- flexible mortgage discount equal to 1/3 of the Central Bank key rate
- free SberPrime+ subscription, discounts on partner company products
- referral bonus for recommending friends to the Sber team.
