Senior Data Scientist - Graph ML & Entity Linking

Sii Poland; Kraków; On-site; PLN 180,000 - 260,000; Full time

Benefits offered by this job

Great Place to Work

Centre of internal trainings

Profit sharing

Open and accessible management team

Medical care

Job summary

Sii Poland seeks a Senior Data Scientist to build an AI-powered operating system for healthcare marketing, focusing on entity extraction, linking, and resolution at scale. You will reconcile large, fragmented datasets into reliable entities and attributes to enable audience insights and value creation in life sciences.

You will implement probabilistic linking, calibrate match probabilities, and work with graph ML techniques to improve data quality and system performance while collaborating with

Qualifications

• 5+ years shipping production ML or data-science work, including entity linking and resolution at scale.
• Proficient Python with production-grade, tested, and type-hinted code.
• Strong SQL and experience with FastAPI, Docker, pytest, Git, and CI/CD practices.
• Experience with probabilistic match scoring, thresholding and evaluation.
• Familiarity with graph algorithms and graph ML techniques, including embeddings and GNNs.
• Experience with data/ML engineering, ETL over large datasets and data-quality monitoring.
• Knowledge of distributed SQL warehouses (Snowflake/BigQuery/Databricks) and graph technologies (Neo4j/Amazon Neptune).
• Advanced English

Responsibilities

• Extract entities and attributes from diverse sources (warehouses, registries, documents).
• Design and implement probabilistic linking and deduplication across large healthcare datasets.
• Own end-to-end linking pipeline with scoring and calibrated probabilities.
• Define link quality metrics: precision, recall, calibration, error analysis.
• Link entities to controlled medical vocabularies for consistency.
• Utilize graph representations and graph ML (embedding, clustering, link prediction).
• Build and maintain data/graph estate, including warehouse transformations and monitoring.
• Improve performance of algorithms with changing data sources and volumes.

Skills

Python

SQL

Graph ML

GNNs

Probabilistic methods

CI/CD

ETL

English

Tools

Snowflake

BigQuery

Databricks

Neo4j

Amazon Neptune

FastAPI

Docker

pytest

Git

Job description

Sii Poland seeks a Senior Data Scientist to build an AI-powered operating system for healthcare marketing, focusing on entity extraction, linking, and resolution at scale. You will reconcile large, fragmented datasets into reliable entities and attributes to enable audience insights and value creation in life sciences.

You will implement probabilistic linking, calibrate match probabilities, and work with graph ML techniques to improve data quality and system performance while collaborating with