Working in a team developing the world's most advanced banking systems in cybersecurity. You will implement and subsequently support new directions within our team, and therefore will have the opportunity to prove yourself by building systems from scratch without the baggage of accumulated problems, as is often the case with old established solutions.
Responsibilities
Designing and developing scalable, fault-tolerant, and observable agent platforms based on LangChain/LangGraph:
- creating and supporting multiple parallel agents with different roles, memory backends, and toolsets
- implementing complex multi-agent processes with branching conditions, recovery mechanisms, and human involvement
- state management strategy (state saving, graph versioning)
- choosing or creating alternatives/extensions to LangChain if standard capabilities are limited (e.g., custom executors, tool routers, hybrid agent frameworks).
Requirements
- higher education in IT
- two years of industrial Python development experience
- experience with big data storage systems: ClickHouse, Hadoop, Big Data
- expertise in LangChain and LangGraph: deep understanding of architecture, experience writing custom components and extending basic functionality.
- advanced PostgreSQL skills: designing high-load databases, using vector indexes (PGVector/hnsw/ivfflat) for semantic search in RAG systems
- mentoring and leadership: ability to lead a team, conduct quality code reviews, assess technical debt, and define product development strategy
- knowledge of risks and protection methods when working with machine learning models: protection against prompt injection, data leaks, prevention of artifacts (hallucinations), and sandboxing for tools
- 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 use of AI for analysis, generation, and automation.
Conditions
- comfortable office at Ryazan, Semashko St., 14
- option to choose a convenient schedule – office/hybrid
- annual salary review, annual bonus
- corporate gym and recreation areas
- over 400 educational programs from SberUniversity for professional and career development
- 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 SberPrime+ subscription, discounts on partner company products
- reward for recommending friends to the Sber team.
