I build stuff related to compilers, deep learning, high performance computing and systems.
I’m currently doing systems research at Anthropic in San Franscico. We work on scaling large language models to build reliable, interpretable and steerable AI systems.
Previously, I studied computer science, at ETH Zurich (2017—2021) and Oxford (2021—2022).
Email me about anything, I love getting mail! You can also find me on github or linkedin.
Microsoft Research (Cambridge, UK): worked on scalable neural rendering and architectural extensions to ONNX Runtime with Tim Harris and the FastNeRF authors.
Scalable Parallel Computing Laboratory (Zurich, CH): worked towards a paper submission for daceml with Tal Ben-Nun and Torsten Hoefler.
Oracle Labs (Zurich, CH): developed a web-scale, graph neural network anomaly detection pipeline and PGX.ML, a graph machine learning library, with Rhicheek Patra and Damien Hilloulin.
Araneum Technologies (Zurich, CH): worked on applied graph machine learning in the banking sector.