Senior Data Scientist for Support Automation Team

Senior Data Scientist for the Support Automation Team

About the Team

Our team develops and maintains algorithms and tools for automating the work of customer support.

Our main goal is to automate the resolution of as large a share as possible of the flow of user requests that have been forced to contact support. We also work to ensure that the quality of automatically resolved requests is high, and the time support agents spend on resolving requests is reduced.

Examples of Future Tasks:

• develop and implement models for determining the topic of user requests (over 500 classes of various topics, which are constantly expanding with new ones and merging with each other);

• maintain and improve existing models and heuristics for various classifications of requests — from simple rules and heuristics to ML systems with online inference;

• analyze the effectiveness of solutions both on historical data and in production, taking into account not only offline metrics for solving ML tasks but also business metrics;

• conduct A/B tests and deploy models to production;

• set up annotation collection and control its quality (both for annotation by assessors and for using LLM solutions or mixed formats for obtaining labeled datasets);

• work together with the LLM team on creating and fine-tuning LLM agents that help users solve their problems based on the specific topic of the request;

• find non-trivial and effective solutions to real business tasks;

• improve existing automation methods, adapting them to a constantly changing external environment based on data and feedback from our users and support agents;

• experiment with SOTA machine learning methods in cases where the application of such methods is justified by the task being solved;

• design and implement end-to-end ML solutions;

• monitor degradations, track metrics in production, and participate in the continuous improvement of models after launch.

It would be great if you:

• have at least five years of experience in Data Science;

• possess a deep understanding of key methods used in solving machine learning tasks and the applicability boundaries of these methods;

• have worked with different data modalities and understand which ML/DL methods are applicable in specific business tasks;

• have experience solving various Data Science tasks using Python;

• understand the principles of production model operation in a near-real-time environment;

• have a higher education in applied mathematics, statistics, ML, or related fields;

• are proficient in SQL and able to extract the necessary data for analysis and model training;

• can evaluate not only the quality of models when launching a new project but also its change over time;

• when launching a model, operate not only with ML metrics but also evaluate the impact of the developed solution on the business metrics for which the team is responsible;

• can read technical articles and documentation in English;

• have experience in support automation or in automating other similar business processes (will be a plus).

Working with us is:

• an opportunity to improve the experience of millions of users;

• interesting and challenging tasks at a large scale;

• a strong team that is always ready to help;

• the opportunity to learn and try new things, with powerful hardware for this;

• a training budget that can be spent on courses or professional literature;

• care for health: from day one, you will have VHI with dentistry, a therapist and a massage therapist are available at the office;

• the opportunity to work remotely or from offices in four cities in Russia.