Company:** Sberbank PJSC
Location: Moscow, RU
Employment Type: FULL_TIME
Junior ML engineer for the acquisition product pricing team for corporate urgent funds. The goal is effective pricing: elasticity models, yield RL-optimizer, individual rate recommendation, with models deployed to production.
Tasks:
- Conduct analytics and monitor model performance
- Collect and prepare data, perform EDA and feature engineering
- Develop new ML models
- Optimize data/model/inference pipeline scripts
- Prepare project code for production, design and conduct A/B tests
Requirements:
- Higher education in a technical field
- At least one year of relevant ML experience
- Strong mathematical foundation: understanding of gradient descent, characteristics of main distributions, PCA and OLS, basic statistical hypothesis testing
- Proficient in Python and SQL, ability to understand others' code
- Proficiency in essential data analysis libraries: pandas, numpy, scipy, matplotlib, statsmodels
- Deep understanding of classical ML algorithms (linear/logistic regression, decision trees, ensembles) and basic DL knowledge
- Proficiency in ML/DL frameworks: sklearn, pytorch, transformers
Conditions:
- Comfortable modern office near Kutuzovskaya metro station
- Hybrid work format
- Annual salary review, quarterly and annual bonuses
- Corporate gym and recreation areas
- Over 400 educational programs from SberUniversity
- Adaptation program and supervisor support at the start
- Expanded voluntary medical insurance (VMI), preferential insurance for family and corporate pension program
- Flexible mortgage credit discount, equal to 1/3 of the Central Bank's key rate
- Prime subscription with the possibility of sharing with three close contacts
- Reward for recommending friends to the Sber team
Skills:
- Python
- SQL
- pandas
- numpy
- scipy
- matplotlib
- statsmodels
- sklearn
- PyTorch
- transformers
- Reinforcement Learning
- multi-armed bandits
- ML
- DL
- AB-tests
