Silas Brack

ML Engineer —

I develop AI and ML models and deploy them to production at Saxo Bank. This means both training in-house models and using open-source pre-trained models. In my time at Saxo, I've worked on many projects, including multiple client-facing products my team has released:

A representation learning model that learns which stocks Others were interested in for a given stock. This model was our first to be integrated into the Saxo Bank platform and used by our customers. As of February 2025, this model has seen a continuous increase in the number of interactions, and is currently sitting at well over 100 000 monthly interactions.
A customer support chatbot which showed a 170% improvement over previous solutions in reducing client interactions requiring human support. My implementation also reduced costs by around $150 000 a year, eliminated several highly time-consuming manual steps, and was trivial to extend to all languages covered by Saxo.
A recommender engine designed to be simple and extensible.

Previously, I've also worked as a C# developer at MAN Energy Solutions.

I did my master's in Mathematical Modelling and Computation at the Technical University of Denmark. During my thesis, “Effortless Bayesian Deep Learning: Tapping Into the Potential of Modern Optimizers” I worked on implicit matrix algorithms for performing the Laplace approximation in Søren Hauberg's group in the section for Cognitive Systems of DTU Compute. We also worked on applying the Laplace approximation to metric learning, which we published at NeurIPS. “Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval,” in Advances in Neural Information Processing Systems, 2023.

Academically, I'm interested in machine learning and statistics, from deep learning to network science to Bayesian inference to forecasting. I love applied math and writing code, so I try to do as much of those as possible. I'm also interested in the intersection of science and society, and science communication is quite important to me. I spend a lot of time trying to learn more about how to effectively communicate ideas and generally just enjoy teaching.

In my spare time, I try to learn more about fields I'm less well-versed in. Right now, that means economics, philosophy, paleontology, and history. I try to make the most of life by learning and teaching, going on walks in nature, appreciating beauty wherever I can, and by (mostly) doing things I enjoy. Because of this, I try to spend my time coding, reading, watching films and series, and listening to music. I also really like to cook.