Omschrijving

Data engineer bridging technical execution and business strategy. My experience lies in building production ML pipelines for healthcare applications while managing international stakeholder coordination. I have a strong foundation in data engineering (Python, R, GCP) complemented by international business background. I possess proven skills in teamwork, insights presentation, and multilingual communication (Polish, English, German, Dutch). Passionate about solving complex problems in fast-paced collaborative settings.

Talen

Pools
Tweetalig / moedertaal
Nederlands
Beperkte professionele capaciteit
Engels
Tweetalig / moedertaal
Duits
Beperkte professionele capaciteit

Voorkeuren voor werkplek

Uitsluitend remote

Werkt voornamelijk remote

CapsicoHealth, Inc.
Data Engineer
september 2025 - januari 2026 (4 maanden)
Palo Alto, CA, USA
• · Architected complete end-to-end ML prediction pipeline integrating REDCap patient data retrieval, causal inference model execution (320+ models), and automated clinical decision support delivery, allowing to predict patient drug response in seconds.
• · Coordinated cross-functional collaboration with 4 stakeholders across Denmark, Netherlands, Germany, and US to align technical requirements with clinical workflows and regulatory constraints.
• · Developed RESTful API infrastructure using Flask and Python to orchestrate data flow between 320+ prediction models (Causal forest, XGBoost), implementing parallel processing for scalable model execution.
• · Built feature engineering pipeline handling medication normalization, dose standardization, and healthcare-specific data transformations using Python/R integration via secure subprocess management.
Docker Python artificial intelligence Machine learning
CapsicoHealth, Inc.
Data Engineering Intern
juli 2025 - september 2025 (2 maanden)
Palo Alto, Verenigde Staten
• · Supported developing and validating 8 causal inference models (Causal forest, XGBoost) for treatment effect predictions, establishing foundation for production healthcare ML system.
• · Engineered data validation framework ensuring input data quality for R-based statistical models, implementing type checking, range validation, and error tracking for patient records.
• · Created inference execution system integrating R statistical models with Python-based pipeline, automating previously manual model deployment and reducing execution time by implementing subprocess-based model calls.
• · Collaborated with clinical teams to translate medical domain requirements into technical feature specifications and model metadata schemas.
Tilburg University (Marketing and Communication)
International Student Assistant
september 2021 - december 2025 (4 jaren en 3 maanden)
Netherlands
Coordinator of international visits - managing a team of over 40 students by coordinating logistics, scheduling, and seamless experience for the visitors. Maintaining partnerships with external stakeholders, and improving the relationships between the university and the industry partners, e.g. high school counselors.