Senior Data Scientist: Scalable ML for Healthcare AdTech

Sii Poland; Wrocław; On-site; PLN 200,000 - 280,000; Full time

Benefits offered by this job

Great Place to Work

Centre of internal trainings

Profit sharing

Medical care

Regular integration events

Job summary

Sii Poland is seeking a seasoned ML engineer to design and implement probabilistic methods for entity linking and matching across large healthcare datasets. You will train scalable models and extract signals from heterogeneous data, contributing to the analytics platform for programmatic advertising and data intelligence.

The role emphasizes Python-based ML workflows, SQL proficiency, and experience with major ML libraries.

Qualifications

• 5+ years of experience in training and monitoring ML models for production use.
• Experience with data and ML engineering, including ML-facing ETL over very large datasets.
• Practical experience with probabilistic methods for entity linking, matching, imputation, scoring, and evaluation.

Responsibilities

• Measure existing model performance and identify improvement paths.
• Own the design of new methodologies and train next-gen models for scalability.
• Extract unique entities and sparse attributes from diverse sources.
• Design and implement probabilistic entity linking across large healthcare datasets.
• Explore graph technologies and theory to support analytics.
• Build and own analytics data store, evaluation, and monitoring pipelines.

Skills

Python

Scikit-learn

PyTorch

LightGBM

Splink

SpaCy

Hugging Face

SQL

Tools

Snowflake

BigQuery

Databricks

Neo4j

Job description

Sii Poland is seeking a seasoned ML engineer to design and implement probabilistic methods for entity linking and matching across large healthcare datasets. You will train scalable models and extract signals from heterogeneous data, contributing to the analytics platform for programmatic advertising and data intelligence.

The role emphasizes Python-based ML workflows, SQL proficiency, and experience with major ML libraries.