IT B2C is the largest ecosystem in Sber. There are over 8,000 of us in 18 cities across Russia. We are involved in the development and evolution of retail solutions, helping to make the Bank's services more accessible, secure, and user-friendly.
We are waiting for you!
About us:
We develop agent RAG systems that help the company improve customer experience through personalized solutions.
We already have a working product that is in production and brings value. Currently, the team is actively working on new applications of the technology and improving the quality of existing ones.
Responsibilities
Under the guidance of a mentor, conduct experiments to improve agent RAG systems:
- improve quality measurement methods: annotation, benchmark collection, and llm-as-a-judge.
- improve search by training models and the quality of the sources themselves.
- optimize and improve response generation.
- together with engineers from the team, deploy new models/approaches to production.
- develop integrations for reaching new customer touchpoints.
- conduct code reviews, monitor code quality, write tests.
- develop and implement new services with ML models.
Requirements
- knowledge of the fundamentals of classical ML and NLP/LLM: classical tasks and architectures/approaches for solving them, metrics, model training process.
- confident knowledge of Python and various ML/DL frameworks: PyTorch, Transformers, PyMorphy, etc.
- knowledge of RAG fundamentals: understanding what tasks it is used for, what problems it solves, and how to implement a basic approach without using Langchain.
- proficiency in the basic set of development skills: Bash, Git, etc.
- pet projects/competitions for solving NLP tasks: text classification, summarization, search, etc.
Conditions
- office work format (optional)
- annual bonus and annual review
- extended voluntary medical insurance from day one + dentistry and preferential family insurance.
- Sber's corporate university, internal educational platform, participation in IT conferences.
- office on Kutuzovskaya with recreation areas and a gym.
- 90 days of remote work from any region of the Russian Federation (not applicable for support).
- preferential mortgage at Sber, corporate pension program, SberPrime+ subscription, discounts from partners and services of the group of companies.
