Description

IT B2C is the largest ecosystem at Sber. We are more than 8,000 people across 18 cities in Russia. We are engaged in the development and enhancement of retail solutions, helping to make the Bank's services more accessible, secure, and convenient.

We are waiting for you!

We are a team of experts united by a common passion for artificial intelligence and recommender systems (RecSys). Our main goal is to create a modern, scalable recommendation platform capable of anticipating user expectations by offering personalized recommendations at every stage of their interaction with the Sber ecosystem. Our solutions cover a wide range of industries: from finance and e-commerce to entertainment and healthcare.

We are transforming the classic content and goods consumption experience by implementing a conversational interface for interaction. Our goal is to create a system that not just ranks items, but acts as a consultant for a person: it understands intentions, can suggest content or products based on needs, proactively identifies preferences through prompting questions, and explains the logic behind the selection.

We are looking for a Senior LLM Engineer to design and implement conversational recommender systems.

Responsibilities

• Develop and implement LLM agents for conversational recommendations across various industries within the Sber ecosystem
• Develop systems based on Retrieval-Augmented Generation (RAG)
• Develop a methodology for evaluating the quality of LLM agent responses for recommendation tasks and establish a process for tracking metrics.

Requirements

• 3+ years of experience in Data Science / ML-Engineering.
• Foundational knowledge in building ML systems and evaluating their quality
• Understanding of the principles for building assistants based on LLMs
• Proficient in Python, experience in developing custom LLM agents and microservices based on them.

Will be a plus:

• Experience in the field of search or recommender systems
• Experience in adapting LLMs for custom tasks using PEFT and RLHF.

Tech Stack:

Python, LangGraph

Conditions

• Hybrid/office work format (optional)
• Annual bonus and yearly salary review
• Extended corporate health insurance from day one + dental and preferential insurance for family
• Sber Corporate University, internal educational platform, participation in IT conferences
• Office at Kutuzovskaya with relaxation areas and a gym
• 90 days of remote work from any region of the Russian Federation (not applicable for support roles)
• Preferential mortgage at Sber, corporate pension program, SberPrime+ subscription, discounts from partners and services of the group of companies.