Rickard Karlsson

Hi, I'm Rickard. I'm currently in stealth mode, working as a scientist and engineer on something big.

I recently completed my PhD in Computer Science (cum laude) at Delft University of Technology, with stints at Harvard and Booking.com. My work focused on how to answer causal questions from data more safely, especially by combining randomized controlled trials with observational data using flexible machine learning models. The aim was to make causal inference more reliable and less dependent on very large datasets. I'm originally from Sweden, where I did my BSc in Engineering Physics and MSc in Engineering Mathematics at Chalmers University of Technology. During my studies I also interned at NASA Goddard Space Flight Center.

Alongside my research, I've developed several open-source tools. These include causal-falsify, a Python package implementing methods to detect unmeasured confounding in observational data, and rct-checker, an LLM-based tool that automatically extracts table data from medical papers on randomized controlled trials and checks for statistical irregularities.

Outside work, my biggest, and probably most expensive, interests are triathlons and electronic music.