I am an ELLIS PhD candidate at the University of Amsterdam working with Wilker Aziz, Barbara Plank and Raquel Fernández.
I am interested in understanding how large language models represent uncertainty, and if we can disentangle uncertainty that arises from the data (e.g., underspecified, subjective or ambiguous language) from uncertainty related to a model (e.g., lack of knowledge or reasoning). Ultimately, I think that uncertainty should power better decision-making.
I am part of the Dialogue Modeling Group in Amsterdam and MaiNLP at LMU in Munich. Previously, I interned at the Allen Institute for Artificial Intelligence in Seattle and spent 2.5 years as ML engineer at DPG Media working on large scale news recommendation.
News
Blogposts
Occasionally I write blogposts. You can find them below.
Can Coding Agents Help Write Scientific Code Responsibly?
I’ve been experimenting with Claude Code to write research code for several months now. When...
Posted by
Joris Baan
on
October 17, 2025 ·
12 mins read
Thoughts on using AI for scientific research and software engineering
As a PhD candidate doing AI research, and a former ML engineer, I am not...
Posted by
Joris Baan
on
July 09, 2025 ·
10 mins read
Designing, Building & Deploying an AI Chat App from Scratch (Part 2)
Cloud Deployment and Scaling
Posted by
Joris Baan
on
January 14, 2025 ·
34 mins read
Designing, Building & Deploying an AI Chat App from Scratch (Part 1)
Microservices Architecture and Local Development
Posted by
Joris Baan
on
January 14, 2025 ·
31 mins read
Implementing a Transformer From Scratch
7 Things You Might Not Know About the Transformer
Posted by
Joris Baan
on
March 25, 2022 ·
18 mins read