ML Engineer / Python Developer (Recommendation Systems)

IT B2C is the largest ecosystem in Sber. There are over 8,000 of us in 18 cities across Russia. We are engaged in the development and evolution 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 recommendation systems (RecSys).

Our main task 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.

The development of our platform is built around the implementation of new SOTA models. We follow global trends, experiment with new approaches, implement them as part of the platform, and bring them to specific business applications. We are looking for a Machine Learning Engineer to join the team to bring the Bank's recommendation models into production. We work with a huge amount of data and high-load services, which makes our work not only important but also technically interesting. The development of the recommendation platform product within the Bank also directly depends on us, as we determine its key growth points. If you resonate with the idea of being a pioneer and want to be at the origins of new technology, join us!

Responsibilities

• Development and improvement of End-to-End ML-pipelines
• Development of production data processing pipelines
• Working with Sber's huge data volumes (petabytes) on PySpark, researching approaches to their application in models
• Writing efficient and scalable code for training and inference of models on PyTorch, conducting experiments on a GPU cluster
• Performance optimization of code for processing large data arrays or high-load online recommendation services;
• Mentoring junior team members, sharing knowledge and expertise.

Requirements

• Mathematical background
• Good knowledge of Python and key frameworks for working with data (PySpark, PyArrow, Pandas)
• Experience in writing high-quality production code
• Experience in writing industrial data processing pipelines containing many steps, dependencies, and complex logic
• Experience using Airflow (or other industry-standard pipeline orchestrators such as Luigi, Dagster, etc.)
• Good understanding of SQL / NoSQL databases
• Experience using GigaChat, Kandinsky, and similar products, skills.

Technology Stack:

• Python, PySpark, Airflow, Kubernetes, FastAPI, S3, PyTorch, MLFlow, Jira, Confluence, Git.

Conditions

• Hybrid/office work format (optional)
• Annual bonus and annual review
• Extended voluntary medical insurance from the first day + dentistry and preferential family insurance
• Sber Corporate University, internal educational platform, participation in IT conferences
• Office at Kutuzovsky Prospekt 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.