I'm a vision-AI researcher and engineer with a strong pull toward practical perception and image understanding. I work hands-on on new model and algorithm development, adapting ideas from across ML into vision, and carrying them through to solid, deployment-ready systems.

In my current role, I've had the chance to grow with the company from an early stage and help shape how we do applied research for industrial computer vision. My day-to-day lives at the intersection of reading and stress-testing new ideas, and turning them into specialized solutions that solve concrete industrial tasks - defect detection, localization, counting, and more. I enjoy owning the full algorithmic journey: designing approaches, training and evaluating models, and translating them into deployment-ready systems.

Before this, I did my Master's in Machine Learning at ETH Zurich, and I've been lucky to work across a range of vision topics. At Google, my thesis focused on 3D indoor scene understanding and point-cloud denoising; earlier, at Disney Research, I explored generative methods for synthetic mouth-movement creation.

Outside of work, I'm happiest when I'm building or exploring something - setting up homelabs and self-hosting services, tinkering with networks, or experimenting with music production. And when I need to reset, I head for the mountains for a hike or trek.