Tuna Yildiz

Tuna began his motorsport journey in Formula Student, learning to squeeze performance and reliability from every sensor channel the team could afford. That student-car experience led him to professional racing in Ferrari Challenge, GT3, GT4 and Clio Cup where he spent race weekends buried in high-frequency telemetry, hunting for the tenths that separate podiums.

Holding an M.Sc. in Computational Science from the University of Zurich and a Mechanical Engineering degree from Rutgers, he specializes in machine-learning pipelines that bridge physics intuition and data-driven pattern-finding—everything from brake-wear‐prediction models to turn-by-turn driver-coaching agents.

Tuna’s toolbox spans cloud architecture, high-performance computing and modern LLM stacks; he has led teams that deployed real-time dashboards, retrieval-augmented chatbots and predictive-maintenance systems across motorsport and industrial settings.

Whether trackside at Spa or iterating code in Zurich, he focuses on a single goal: turning raw, high-velocity data into clear, actionable decisions that win races and protect hardware.

‍