Data Engineer at Rabobank·Leiden, NL

WHERE I'VE WORKED AND STUDIED

Experience

Work & research

Now

Data Engineer Rabobank

Data pipelines and ML infrastructure in production: MLOps, CI/CD, infrastructure as code, automated testing and monitoring.

2024–25

Research: Multimodal Sound Symbolism Leiden University

Do vision-language models pick up the same sound–meaning associations humans do? Code on GitHub ↗

Education

2024–25

MSc Computer Science: Data Science & AI Leiden University

Thesis: Cross-Modal Sound Symbolism in Vision-Language Models. Grade 8/10.

2020–23

BSc Computer Science Vrije Universiteit Amsterdam

Minor in Data Science.

Full résumé →CV (PDF) ↓

WHAT I WORK WITH

Skills

Data & Analytics

PlatformDatabricks
ComputeApache Spark
QuerySQL · Pandas
AzureData Factory · Synapse

Languages

Python
SQL
Scala
Bash · C/C++

ML & AI

BoostingXGBoost · LightGBM · CatBoost
Deep learningPyTorch
Ops & explainMLflow · SHAP
LatelyAgentic AI

Cloud & DevOps

Azure · AWS · GCP
Terraform
Docker · K8s
CI/CD

WRITE-UPS, NOTEBOOKS AND FINAL MODELS

Projects

Kaggle Competitions

Rainfall Prediction

Top 0.2%

Predicting daily rainfall from weather features. After feature engineering and K-fold cross-validation, a well-tuned KNN beat heavier ensembles. Finished rank 5 of 2,529.

House Prices Prediction

Top 1%

Regression on house sale prices, using SHAP to see which features drove the predictions. Over several versions I found data leakage in the target, which explained an accuracy jump that had looked suspicious.

Loan Payback Prediction

Silver · Top 4%

Binary classification of loan default risk from credit metrics, debt-to-income ratios and payment history. An ensemble of XGBoost, LightGBM and CatBoost, with SHAP for explainability.

Music BPM Prediction

Silver · Top 5%

Predicting a track's tempo from raw audio, combining signal-processing features with features based on music theory, then gradient boosting on top.

Road Accident Risk

Top 8%

Interaction features that capture how time of day and weather combine. Training ran in a Docker pipeline tuned with Optuna, so results were reproducible.

Bank Marketing

Top 17%

Predicting whether a customer responds to a campaign within seven days. A YAML config defined feature sets, models and hyperparameters, making them quick to swap and test.

Podcast Listening Time

Top 16%

Estimating how long a listener stays with an episode. Temporal features and a stacked ensemble picked up signal that no single model found.

Optimal Fertilizer

Top 28%

Recommending fertilizer types per field as a multi-label problem, optimizing directly for MAP@3 rather than plain accuracy.

Titanic Survival

Top 15%

The classic first competition. I used it to learn feature engineering basics and XGBoost before moving on to messier datasets.

Spaceship Titanic

A harder follow-up, and mostly a lesson in overfitting: pushing too hard on validation score hurt generalization until I paid closer attention to feature correlation.

Credit Card Fraud

Fraud detection on a heavily imbalanced dataset. The key lesson: apply SMOTE inside each K-fold split, not before it, or the validation scores mislead.

Personality Type

Top 34%

Classifying personality type from a small, noisy dataset. Oversampling and Bayesian hyperparameter optimization made the biggest difference.

Calorie Expenditure Prediction

Estimating calories burned from workout duration, heart rate and body metrics, engineered into features for gradient boosting.

Exam Score Prediction

Predicting exam performance from study habits and demographic features, blending CatBoost and LightGBM instead of relying on a single model.

Customer Churn Prediction

Stacking CatBoost and XGBoost; weighting their outputs balanced the different ways each model tends to fail.

Irrigation Need Classification

Multi-class classification of irrigation need from soil composition and weather data.

EV Purchase Prediction

Predicting the probability that a buyer purchases an electric vehicle, treated as probability estimation rather than yes/no classification.

Kaggriculture

An agent plays against an opponent in a simulated farm economy (plant, water, harvest, sell) and wins by out-planning the other strategy in real time.

Personal Projects

SVM Heart Disease Classification

Classifying heart disease risk with a support vector machine, using feature scaling and kernel tuning to get the decision boundary right.

RNN Solana Price Prediction

A recurrent neural network on historical market data, to see how much signal a sequence model can find in noisy crypto prices.

Thyroid Cancer Classification

Exploratory analysis and classification on a thyroid cancer risk dataset, looking at which clinical features actually separate the classes.

Knapsack Optimization

Solving variants of the classic knapsack problem: a break from ML to work through combinatorial optimization by hand.

Credit Card Analysis

My own exploration of credit card transaction data, separate from the Kaggle fraud-detection write-up.

Function Notebook

Reusable data science helper functions that grew alongside my other projects, and later became a proper utilities library.

Open Source

ML Utilities Library

Reusable ML components and helpers taken from code I kept rewriting, so common preprocessing and evaluation code doesn't start from scratch each time.

Multimodal Sound Symbolism

Code for my MSc thesis on cross-modal sound symbolism in vision-language models.