Data & DevOps Engineer
I specialize in MLOps, data pipelines, and turning experimental models into production-ready solutions. With a proven track record in competitive machine learning and a focus on infrastructure as code, I focus primarily on data science, data engineering, and DevOps.
Leiden University
Specialization: Data Science & AI
Thesis: Cross-Modal Sound Symbolism in Vision-Language Models
Vrije Universiteit Amsterdam
Minor: Data Science
Rabobank
Building and maintaining scalable data pipelines and ML infrastructure in production environments. Specializing in MLOps practices, containerization, CI/CD automation, and cloud-based data engineering. Main duties include application maintenance, production deployment through infrastructure as code, creating data pipelines, automated testing, and monitoring systems.
Leiden University
Investigated cross-modal sound symbolism in vision-language models. The research combined computational linguistics, computer vision, and cognitive science to analyze how multimodal AI models process and represent sound-meaning associations across cultures. Achieved grade of 8/10.
View on GitHub ↗A collection of competitive machine learning projects showcasing technical evolution from experimentation to deployment.
Experimented with feature engineering, K-Folds, and ensemble methods. Discovered that simpler algorithms (KNN) can outperform complex ensembles when properly optimized. Achieved rank 5 out of 2,529 participants through careful algorithm selection and hyperparameter tuning.
Major breakthrough in regression techniques. Incorporated domain knowledge and used SHAP for feature importance analysis. Achieved rank 37 out of 3,935 participants, ultimately discovering and exploiting data leakage for near-perfect score.
Binary classification for financial risk assessment. Applied sophisticated feature engineering combining credit metrics, debt-to-income ratios, and payment history. Ensemble of XGBoost, LightGBM, and CatBoost emphasized interpretability using SHAP values. Rank 172 / 3,724.
Predicting song tempo from audio features. Combined signal processing with machine learning, leveraging music theory for feature engineering. Gradient boosting models captured complex patterns in audio data. Rank 131 / 2,581.
Ensemble methods predicting accident risk. Created temporal and weather interaction features. Containerized training pipeline using Docker for reproducibility. Rank 313 / 4,082.
Customer response prediction in 7 days. YAML configuration management for rapid prototyping. Rank 576 / 3,367.
Time series regression with temporal features and advanced stacking. Rank 536 / 3,310.
Multi-label classification with MAP@3 optimization and agricultural domain knowledge. Rank 732 / 2,650.
First Kaggle experience. Feature engineering fundamentals and XGBoost. Rank 2,331 / 15,346.
Lessons on overfitting and feature correlation. Rank 613 / 1,816.
Imbalanced data with SMOTE. Learned proper application within K-Folds.
Limited data with advanced oversampling and Bayesian optimization. Rank 1,379 / 4,067.
Reusable machine learning components and helper functions. Collection of battle-tested utilities for data science workflows.
View on GitHub ↗