Senior Data Engineer / Data Scientist

Quick Facts

• Role: Senior Data Engineer / Data Scientist (hybrid)

Description

You will develop and evolve large-scale production data pipelines, apply machine learning for segmentation and scoring, and integrate data with programmatic advertising platforms. Work includes identity graph processing (cookie/GAID/cross-device linking and deduplication), geolocation analytics (WiFi signals, polygons, catchment area, footfall, geospatial analysis), and measurement/reporting automation (lift, incrementality, campaign attribution). The role emphasizes documentation, standards, and translating model results into business decisions.

Responsibilities

• Build and maintain production-scale data processing pipelines using Python and Spark (batch and distributed processing)
• Process identity graph data: connect and deduplicate identifiers and maintain graph quality and scale
• Process geolocation data: WiFi signals, polygons, catchment area, footfall, and geospatial analyses
• Build and evaluate models: look-alike, scoring, segmentation, and segment quality assessment
• Automate retail media measurement reports (lift, incrementality, campaign attribution) and collaborate with analytics
• Integrate with programmatic platforms (DV360, Adform, Google Ad Manager / DDP)
• Document solutions and establish working standards so knowledge stays in the team

Requirements

• Minimum 5 years in data engineering or data science in a production environment
• Python
• Advanced SQL; PostgreSQL experience including complex queries, optimization, and large-table work
• Spark for distributed processing at scale
• dbt for transformations, tests, and model documentation
• Pipeline orchestration and data pipeline maintenance
• Applied ML/modeling experience (scoring, classification, look-alike, similarity measures, model quality evaluation)
• Self-sufficient working style and comfort in a changing environment

Benefits

• Work on unique, proprietary data assets at real market scale
• Direct impact on the product core (evolving what already works)
• Hybrid work from Warsaw; employment form flexible (UoP or B2B)