Hi, welcome to my project portfolio!
My name is Wouter and I am a machine learning engineer & LLM enthusiast. This website has the goal of explaining some projects that I worked on — with the technical challenges we faced and solution architecture designs. In case of questions or support, feel free to email me at wouterwijffels@gmail.com.
Background
MSc Transport, Infrastructure & Logistics — Cum Laude
Delft University of Technology
BSc Industrial Engineering & Management
University of Groningen
Started with operations research and logistics optimisation, moved into data science when the tooling caught up with the problems. Most of my work since has been on the gap between a working notebook and a model that reliably serves predictions in production — deployment patterns, monitoring, multi-country infrastructure.
Centralized monitoring for 15 models and 400+ pipelines with statistical process control drift detection.
Terraform, Lambda, MLflow, Prometheus, Snowflake
Hierarchical item clustering and supplier price comparison via drag-in document search.
OpenAI Embeddings, FAISS, Streamlit
1.3M customer service conversations per year — PII masked, summarized, classified, and auto-filed in CRM.
AWS Bedrock, Lambda, SageMaker, MLflow
Predicts campaign uplift before launch using historical experiment data to replace intuition-based targeting.
Python, Polars, Snowflake, Scikit-learn
Single XGBoost model deployed to 5 countries with different data warehouses and marketing systems via S3.
SageMaker, Snowflake, S3, XGBoost, GitLab CI/CD
NLP mapping of public commodity indices to supplier cost structures for procurement negotiation verification.
Python, NLP, Snowflake, Commodities APIs