Description
We are a close-knit team reimagining how people interact with their bank. Our product is not just a voice assistant for ATMs. It is a unique digital intelligent companion in the financial sphere, which anticipates customer actions and desires, provides consultations and recommendations, understands life situations, and transforms complex operations into a simple dialogue.
We are looking for an experienced engineer to create high-load microservices with full responsibility for the cycle: from task analysis and architecture design to implementation and testing. The key focus is independent work with requirements and the creation of fault-tolerant distributed systems based on AI agents.
Responsibilities
- lead the product direction of system analysis of business requirements when designing architecture and API (REST) for new services
- develop and maintain microservices on FastAPI and interact with related teams to integrate components and ML models into services
- develop prompts and scenarios for generative models
- optimize service performance at all levels: code (asyncio, threading), data storage and queries (advanced SQL, indexes, sharding), caching (Ignite), work with queues (Kafka), creation and optimization of RAG systems for data processing
- participate in designing test scenarios and creating test datasets. Control implementation quality, conduct in-depth defect analysis, determine their root causes.
Requirements
- Python development experience of 2+ years, including independent design of service component architecture based on business requirements and using ML frameworks
- practical experience creating high-load and fault-tolerant microservices on FastAPI, as well as products with ML solution implementation
- deep knowledge in asynchronous applications, advanced SQL (window functions, query optimization), experience with message brokers (Kafka), Docker, Kubernetes
- good knowledge of algorithms and data structures
- understanding of how generative models work (GPT, GigaChat, etc.)
- high culture of collaboration using BitBucket/Jira, careful attention to commits, knowledge of Agile (Scrum) processes.
Will be a plus:
- experience in system/business analysis
- knowledge of modern LLM fundamentals, AI-agent architectures, and experience integrating ML solutions (NLP, LLM) into products
- skills in using AI tools (GigaChat, DeepSeek, ChatGPT) for analysis, generation, and automation
- practical experience with ML/DS frameworks: (LangChain/GigaChain, Scikit-Learn, Pandas, etc.).
Conditions
- comfortable modern office at Kutuzovskaya metro station
- work format: office during adaptation period, then hybrid
- annual salary review, annual bonus
- corporate gym and relaxation areas
- more than 400 educational programs from SberUniversity for professional and career development
- extended voluntary health insurance, preferential insurance for family, and corporate pension program
- free SberPrime+ subscription, discounts on products from partner companies
- referral bonus for recommending friends to the Sber team.
