for the ML solutions development team for a bank. Working with big data in PySpark, preparing data for models and analyzing results.
Tasks:
- Processing and analysis of big data in PySpark: loading, filtering, aggregations, joins, and data enrichment.
- Development and support of data marts and datasets in PySpark for product tasks and ML models: features, aggregates, and historical snapshots.
- Labeling of key client events based on business logic and data analysis.
- Data quality check: searching for duplicates, missing values, anomalous values, and logical inconsistencies.
- Data exploration based on existing data marts: calculating metrics, searching for patterns, formulating simple heuristics, analytical rules, and hypotheses.
- Verification of ML model results and analysis of calculated scores.
- Preparation of feature sets for models.
Requirements:
- Work schedule: from 30 hours per week, full-time format.
- Mandatory tech stack: Python, SQL, Excel, Jupyter.
- Full-time student.
- Student of a Russian university.
- Year of study: 2nd-6th year of Bachelor's/Specialist program or 1st-2nd year of Master's program.
- City of residence: Saint Petersburg.
Conditions:
- Paid internship
- Internship duration: 3 months
- Work schedule: from 20 hours
- Full-time format
- Comfortable modern office
Skills:
- Python
- SQL
- Excel
- Jupyter
- PySpark
