Description
Our team is creating the "Online Property Valuation for Collateral Purposes" product.
The service automates the process of determining the appraised value of property: from vehicles to commercial and industrial premises, based on ML models.
Currently, we are looking for a DS (Data Scientist) capable of leading independent development of classical ML models, communicating with the client, and designing and implementing solutions for business tasks.
Responsibilities
- Lead the End-to-end process of creating ML models:
research of relevant data
building and testing hypotheses
deployment of models into industrial operation
- Coordinate model development with related departments, work on integrations
- Communicate with business clients
- Participate in preparing specifications for data labeling and verification.
Requirements
- Higher education in Mathematics, Computer Science, or Data Analytics
- At least 3 years of experience in Data Science, with implemented and deployed solutions
- Deep expertise in classical ML
- Knowledge of mathematical statistics methods, data analysis algorithms (regression, factor, variance, and correlation analysis) and economic-mathematical modeling (econometric models, neural networks, Bayesian networks, clustering)
- Confident skills in working with Python (jupyter, numpy, scipy, pandas, scikit-learn, xgboost), experience writing production code
- Confident command of data analysis/processing tools/technologies (SQL / Hadoop / Spark / equivalents)
- Experience with databases (PostgreSQL), skills in working with data arrays
- Skills in working with generative AI models.
Relevant experience in collateral valuation, understanding of the principles of operation and design of Backend applications (system design), experience in developing analytics and data visualization tools, experience in building a mature ML process will be an advantage.
Conditions
- Employment according to the Labor Code of the Russian Federation
- Guaranteed income plus performance bonus
- Flexible discount on a mortgage loan, equal to 1/3 of the Central Bank's key rate
- Voluntary Health Insurance (VHI) from day one and preferential insurance for close relatives
- Free SberPrime+ subscription, discounts on products from partner companies
- Corporate pension program
- Company-paid training: online courses in Sber's Virtual School, opportunity to obtain a new qualification
- Employee referral program: you can invite professional acquaintances to the team and receive a reward
- Work format: office or hybrid
- Workplace: Saint Petersburg, Krasnogo Tekstilshchika str., 2.
