Senior Data Scientist - Healthcare AdTech & Graph ML

Sii Poland; Warszawa; On-site; PLN 210,000 - 320,000; Full time

Benefits offered by this job

Great Place to Work

Centre of internal trainings

Profit sharing

Medical care

Regular integration events and trips

Open management

Job summary

Sii Poland is hiring for an ML/AI specialist to design and implement probabilistic methods for entity linking and matching across large healthcare datasets. You will train next-generation models, improve predictive power, and build scalable data pipelines in production.

The role requires 5+ years of ML experience, strong Python data-science skills, and familiarity with SQL-based warehouses (Snowflake, BigQuery, Databricks). English proficiency is essential.

Qualifications

• Minimum 5 years of experience training and monitoring ML models in production.
• Experience with ML/data engineering on very large datasets and data-quality monitoring.
• Proficiency in Python data-science libraries (scikit-learn, PyTorch, LightGBM, spaCy, Hugging Face).

Responsibilities

• Measure model performance and seek improvements.
• Own the design of new methodology and train the next-gen model for increased predictive power, sample efficiency, and scalability.
• Extract unique entities and sparse attributes from heterogeneous sources – both structured and unstructured.
• Design and implement probabilistic entity linking & matching across multiple large healthcare datasets.
• Explore graph technologies and graph theory.
• Build and own analytics data store, evaluation, and monitoring pipelines.

Skills

Python

Data science

SQL

Model monitoring

Probabilistic methods

Graph theory

English

Tools

scikit-learn

PyTorch

LightGBM

Splink

spaCy

Hugging Face

Neo4j

Snowflake

BigQuery

Databricks

Job description

Sii Poland is hiring for an ML/AI specialist to design and implement probabilistic methods for entity linking and matching across large healthcare datasets. You will train next-generation models, improve predictive power, and build scalable data pipelines in production.

The role requires 5+ years of ML experience, strong Python data-science skills, and familiarity with SQL-based warehouses (Snowflake, BigQuery, Databricks). English proficiency is essential.