I am a PhD fellow at the Technical University of Denmark, funded by the Danish Data Science Academy through the Novo Nordisk Foundation and Villum Fonden. I am supervised by Prof. Lars Kai Hansen (Technical University of Denmark) and Prof. Sebastian Weichwald (University of Copenhagen).

Currently visiting Stanford's STAIR Lab under Prof. Sanmi Koyejo, researching mechanistic interpretability and safety alignment for large language models. My research connects trustworthy AI and healthcare, from explainability methods to clinical EEG.

Read More →

Open to collaborations and new ideas.
Reach me at agjma [at] dtu.dk or gjoelbye [at] cs.stanford.edu.