A first post, mostly so this place isn’t empty :)
I’m Yannick, an ML engineer in Zurich working on AI evals, governance, risk, and safety. I’ve been at LatticeFlow AI since 2021, joining as employee #6 after having written my master thesis at LatticeFlow. At LatticeFlow, I first worked on model improvement and data quality for vision and audio models, and in 2024 moved over to working on AI evals and governance for LLMs (benchmarks, red teaming, robustness).
Before that I studied electrical engineering and information technology at ETH Zurich, a bachelor’s from 2015 to 2018 with a focus on signal processing, and a master’s from 2019 to 2021 with a focus on machine learning and computer security. I wrote two papers on adversarial machine learning, at a NeurIPS 2022 workshop and at CyCon 2024.
Away from a keyboard: mountains, kitesurfing, salsa.
Longer version on the about page, or find me on GitHub and LinkedIn. Email:
