Company:** Sber. IT Location: Moscow, RU Employment type: FULL_TIME

Our product is the automated system “Cryptography Services and Infrastructure Functions”.

The system includes:

• A subsystem for accounting for cryptographic information protection tools (CIPF) in accordance with regulatory requirements;

• A subsystem for business monitoring of events related to CIPF accounting and the use of authentication methods;

• An AI agent (low-code/no-code) implementing the functionality of "proactive response" in terms of monitoring business services, as well as a "profile consultant" for internal documents, incidents, and issues related to CIPF.

Our system is implemented on a microservice architecture and has been put into industrial operation. Functional development continues, a backlog has been formed with the business unit until 2027, and there are even more plans!

Many people joined our team from areas not related to cybersecurity, which did not prevent colleagues from actively participating in product development from the first days of work. Development is carried out according to the Scrum methodology, adapted to Sber's IT production process.

Responsibilities

• Preparation and approval of system requirements with the team
• Participation in the development of the AI agent's skills and "tools"
• Analysis and description of internal interactions of the SKIF AS
• Design of interactions with adjacent systems and external consumers
• Participation in the preparation for testing of developed functionality
• Participation in supporting functionality after implementation.

Requirements

• Higher technical education
• At least 2 years of experience as a system analyst: forming business, functional, and non-functional requirements
• Understanding the differences in integration methods: Broker, Queue, Rest-API
• Familiarity with JSON, YAML formats, UML/BPMN notations, designing data structures (SQL/PostgreSQL), REST/API contracts (OpenAPI)
• Understanding of microservice architecture
• Understanding the concept of managing the "idea → code → review → deploy" cycle with the participation of AI agents, understanding the limitations and risks of autonomous code generation
• Understanding of AI patterns: RAG, Agentic workflows, tool use/function calling, agent orchestration
• Understanding of the LLM integration cycle: prompt engineering, guardrails, output quality assessment, logging of agent decisions
• Experience with fine-tuning or working with local LLMs.

Will be a plus:

• 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 analogs in products, skills in creating and using AI agents
• Instrumental use of AI for analysis, generation, and automation.

Conditions

• Comfortable modern office: Poklonnaya St 3k2
• Office work. In the future, a hybrid schedule is possible
• Annual salary review, annual bonus
• Corporate gym and recreation areas
• More than 400 educational programs from SberUniversity for professional and career development
• Adaptation program and manager support at the start (for Junior positions)
• Extended voluntary medical insurance, preferential insurance for family and corporate pension program
• Flexible discount on mortgage loans, equal to 1/3 of the Central Bank's key rate
• Prime subscription with the possibility of shared use with three close people
• Reward for recommending friends to the Sber team.