Wouter Kool
Senior Operations Research Engineer
Amsterdam, North Holland, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolWouter Kool is a Senior Operations Research Engineer with a PhD in machine learning and eight years of experience applying deep learning and combinatorial optimization to real-world logistics problems. He pioneered Transformer-like models for vehicle routing (attention-learn-to-route, ~750 citations and 750 GitHub stars) and earned an ICML honorable mention for stochastic beam search while interning at DeepMind. At ORTEC he led award-winning VRP teams, improved production systems (e.g., travel time prediction, warehouse routing, and a 100x faster event-based simulator) and drove competitions and community events that advanced state-of-the-art VRP solutions. Equally comfortable in research and engineering, he combines fast prototyping in Python with production-grade optimization solvers and a knack for turning academic ideas into operational wins. Colleagues know him as an enthusiastic presenter and competitive problem-solver who consistently finds pragmatic paths to near-optimal results.
8 years of coding experience
5 years of employment as a software developer
Bachelor’s Degree, Business Analytics, 9.0, cum laude, Bachelor’s Degree, Business Analytics, 9.0, cum laude at VU University AmsterdamDoctor of Philosophy - PhD, Machine Learning for Combinatorial Optimization, Doctor of Philosophy - PhD, Machine Learning for Combinatorial Optimization at University of Amsterdam
Dutch, English, German, French
Github Skills (8)
attention-mechanism10
pytorch10
machine-learning10
graph-neural-network10
python10
algorithms8
algorithm8
tensorflow3
Programming languages (4)
Github contributions (5)
wouterkool/attention-learn-to-route
Mar 2018 - Jun 2021
Attention based model for learning to solve different routing problems
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 23 commits, 10 PRs in 3 years 3 months
Contributions summary:Wouter primarily focused on developing and refactoring the attention-based model for routing problems. Their contributions include core model architecture improvements, such as incorporating a graph attention encoder, defining decoding types, and integrating VRP and PCTSP problems. The code changes reflect efforts to improve the model's functionality and adaptability to various routing scenarios, as well as updating the code base to be compatible with the latest version of PyTorch.
model-basedsolveproblemsroutingoperations-research
wouterkool/dpdp
Feb 2021 - Jan 2023
Contributions:8 commits, 6 pushes, 1 branch in 1 year 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.