Senior Data Scientist

Quick Facts

• Role: Senior Data Scientist

• Focus: AI-driven entity extraction and probabilistic entity matching for healthcare marketing data

Description

You will design and implement end-to-end pipelines to extract entities and attributes from heterogeneous sources and to resolve and deduplicate them at large scale. The work includes probabilistic entity linking with calibrated match probabilities, graph-based evaluation, and integration with controlled medical vocabularies to ensure consistency. You will build and maintain data and graph resources, monitor quality, and improve performance as data sources and volumes change.

Responsibilities

• Extract entities and attributes from heterogeneous sources (warehouse tables, registries, documents)

• Design and implement probabilistic entity matching and deduplication across large medical datasets

• Own the end-to-end linking pipeline, including pair evaluation with graph-based scoring and calibrated match probabilities

• Define how linking quality is measured (precision, recall, calibration, and error analysis)

• Link entities and attributes to controlled medical dictionaries for cross-source consistency

• Use graph representations and graph ML techniques (clustering, centrality, link prediction)

• Build and maintain data and graph assets, including warehouse transformations and monitoring

• Optimize performance of existing algorithms as data sources and volumes evolve

Requirements

• 5+ years of production delivery experience in ML/data science, including large-scale entity resolution and deduplication

• In-depth Python experience with production code, tests, and type annotations

• Strong SQL and experience with FastAPI, Docker, pytest, Git, and CI/CD

• Practical experience with probabilistic methods for match scoring, threshold selection, and evaluation/calibration

• Knowledge of graph algorithms and graph ML (embeddings, GNNs)

• Experience with data engineering and ML: large-scale ETL and data quality monitoring

• Experience with distributed SQL warehouses (Snowflake, BigQuery, or Databricks) and graph technologies (Neo4j or Amazon Neptune)

• Advanced English proficiency

Benefits

• Great Place to Work

• Stable financial situation

• Contracts with global brands

• Internal training center

• Many experts to learn from

• Open and approachable management

• Profit sharing

• Passion sponsorship program

• Regular events and integration trips

• Comfortable, well-equipped offices

• MySii application

• Medical care