We offer you the opportunity to join a team working on projects in a new, dynamically developing area of artificial intelligence security. Your tasks will be related to the search and research of vulnerabilities in GenAI models (LLM/MLM) and applications using them, including AI agents. Within a team of experienced experts, you will develop software for automating the research and testing of GenAI model security.
Your responsibilities will include:
- Software development: creation, maintenance, and development of tools for analyzing and searching for GenAI threats, including:
- Development of automation tools for collecting, storing, and analyzing new publications, incidents, and attack methods against GenAI (crawling, information parsing, development and management of storage systems)
- Creation and testing of prototypes (Proof of Concept) for finding GenAI vulnerabilities (python scripts, libraries: flask/fastapi, asyncio, pydantic, langchain/gigachain, AI agents for code generation)
- DevOps: CI/CD, version control (git), software quality testing (pytest, mypy, black), infrastructure for work (linux)
- Implementation of AI PDLC practices: research and application of methods and tools for creating and developing software using advanced AI models.
- Immersion into the ecosystem: studying and practical application of advanced frameworks and libraries for working with LLMs and AI agents.
What is important to us:
- Profile and education: completed higher education in information technology, computer science, applied mathematics, software engineering, or related fields.
- Advanced Python programming skills: understanding of software design and development principles, asynchronous programming, API (REST), ability to write clean (understandable, maintainable) code.
- DevOps skills: experience with git, Linux administration, automation of software development lifecycle stages.
- LLMs and AI agents: experience in effectively applying LLMs for software development.
- English language proficiency sufficient for reading technical documentation and articles.
- Experience in teamwork on development projects: Kanban (sprints, task tracking), Jira/Git/Confluence, presentations, and the ability to clearly explain ideas to the team and agree on requirements.
Will be an advantage:
- Knowledge of information security fundamentals, understanding of cybersecurity risks for LLMs and AI agents: OWASP, MITRE, FSTEC BDU, Sber AI Cybersecurity Threat Model.
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 supervisor support at the start
- Expanded VMI (Voluntary Medical Insurance), preferential insurance for family, and corporate pension program
- Flexible mortgage credit discount equal to 1/3 of the Central Bank's key rate
- Free SberPrime+ subscription, discounts on products from partner companies
- Referral bonus for recommending friends to the Sber team.
