Sberbank's Cybersecurity Center is looking for a highly qualified specialist with knowledge in the field of large language models (LLM) and the ability to effectively apply them to solve business problems. You will work in one of the largest and most technologically advanced cyber security operations centers in our country, ensuring the protection of the bank's critical infrastructure and clients from modern threats.
Your responsibilities will include:
- Formulating hypotheses and conducting experiments to assess system vulnerabilities and identify new attack methods.
- Creating and optimizing high-performance prompts for anomaly analysis, threat detection, and incident prevention.
- Analyzing the effectiveness of applied prompts and developing recommendations for their improvement.
- Working with modern LLMs (GigaChat, Qwen, Deepseek, etc.) to implement innovative solutions in cybersecurity.
- Documenting processes and transferring best practices to colleagues, participating in the development of team standards and methodologies.
What is important to us:
- Successful experience working with large language models (LLM).
- Understanding the specifics of applying LLMs under conditions of increased security requirements.
- Experience in developing and optimizing prompts for solving applied problems.
- Excellent analytical skills and the ability to conduct experiments, test hypotheses, and interpret research results.
- Experience with popular libraries and tools for working with LLMs (LangChain, LangGraph, LlamaIndex, Hugging Face Transformers, etc.).
- Basic IT skills: working with RESTful API, Linux terminal, Git version control system.
- High degree of responsibility, attention to detail, and readiness for continuous professional development.
Will be an advantage:
- Experience developing AI agents.
- Experience in information security.
- Fluency in the Python programming language, sufficient for process automation and integration with LLM APIs.
- Experience implementing Retrieval-Augmented Generation (RAG) methods.
- Experience using products from the LangChain ecosystem beyond LangChain and LangGraph.
We offer:
- Comfortable modern office.
- Office-based work format.
- Annual salary review, annual bonus.
- Corporate gym and recreation areas.
- Over 400 educational programs from SberUniversity for professional and career development.
- Adaptation program and manager support at the start.
- 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.
- Free SberPrime+ subscription, discounts on products from partner companies.
- Reward for recommending friends to the Sber team.
