Prefferd tech

Tech Stack: -

Tech Skills: ML, Deep learning

Expert’s cases:

1. Worked on demand forecasting tasks (boustings, py.spark). One of the sub-tasks was development of analytical reporting (preparation of dashboards, worked with Tableu, Dash, etc.). I was involved in time series forecasting in different domains (worked with autoregressive models, bousting, GluonTS, LSTM and some other models). One of the projects was related to optimization of marketing campaigns (uplift modeling, classical ML models). Used uplift modeling and ML models for multiclass classification. Next was a project on homomorphic encryption, anonymization and tasks to develop a platform to solve optimization problems (airflow, plotly and Dash) and develop models for dynamic pricing.

2. From March 2018 to December 2020, I worked in consulting (technology solutions development) at SAS Institute. The work is related to the development of solutions based on SAS Event Stream Processing (integration processes with RabbitMQ), work with data (DI, SAS Base, SQL) and development of automated testing system (python+selenium), as well as solving optimization problems (work with time series).

3. experience with both classical machine learning models (regression, k-mean, knn, random forest, boustings, etc.) and Deep Learning (CNN, LSTM, RL). Since 2018 I have been teaching computational mathematics (numerical methods) to MIPT students, since last year I still teach lab classes in python (fall semester) and data analysis in python (spring semester).