Responsible for staying uptodate with machine learning literature and using this to drive innovation in our products.
Spearheaded a project for integrating skeletonbased action recognition into the company's product. Performed extensive research, and identified the most viable strategy for implementation.
Developed benchmarking tools to measure reallife performance of human pose recognition models to determine the best model for the company's use case. This led the identification of better models and a deeper understanding of the product's limitations.
Invented a novel method for calibrating multicamera systems, improving accuracy and userexperience, and leading to a patent application.
Developed a service broker and launching system, with capabilities to monitor and log services. This is now a core part of the product and drastically improved developer experience.
Maintained and upgraded Jenkins CI/CD pipelines, improving development experience on all the company's Python projects.
Maintained and improved core systems for deployment of human pose recognition.
Created a holographic augmented reality system using head tracking and a projector to display a 3D scene from the user's perspective.
Initially started a PhD in pure mathematics, later transitioning to applied mathematics (numerical linear algebra).
Authored 5 papers during PhD, of which 4 have accompanying Python codebases. One paper is in pure mathematics, two in computational algebra, one on numerical linear algebra, and one on machine learning.
Taught 3 courses per year as an assistant, receiving consistent positive feedback from students.
Helped as a scientific editor of a science communication journal.
2018/03—2022/12
PhD in Mathematics

University of Geneva
2015—2018
Msc. Mathematical Sciences

Utrecht University (cum laude)
2012—2015
Bsc. Mathematics

Utrecht University (cum laude)
Bsc. Physics and Astronomy

Utrecht University (cum laude)
Streaming Tensor Train Approximation
published in
SIAM Journal on Scientific Computing
joined work with
Bart Vandereycken and Daniel Kressner
TTML: tensor trains for general supervised machine learning
joined work with
Bart Vandereycken
On certain Hochschild cohomology groups for the small quantum group
published in
Journal of Algebra
joined work with
Nicolas Hemelsoet
A computer algorithm for the BGG resolution
published in
Journal of Algebra
joined work with
Nicolas Hemelsoet
Parallel 2transport and 2group torsors
2021/02
Neuroscience and Neuroimaging Specialization

John Hopkins University (Coursera certificate )
2020/09
Genomic Datascience Specialization

John Hopkins University (Coursera certificate )
2019/08
Advanced Machine Learning Specialization

Higher School of Economics (Coursera certificate )
Rik Voorhaar © 2024