I'm a data scientist who bridges the gap between technical possibility and business reality. Currently leading data science initiatives in agri-food, where the right insights can transform entire value chains.
I've learned that the best AI solutions aren't built in isolation. They emerge from understanding the real problem, communicating openly about what's possible, and iterating closely with the people who'll use them. That's the approach I bring to every project—whether I'm building models or leading teams.
Before touching data, I dig into the business context. What decision are we trying to improve? What does success actually look like? The technical solution follows from there.
I translate between technical and business language fluently. Stakeholders know what we're building and why. Teams know what's expected. No black boxes, no jargon walls.
Models that don't ship don't matter. I focus on practical solutions that work in production, with clear metrics tied to business outcomes—not just algorithmic performance.
End-to-end ML pipelines, from feature engineering to production deployment. Specialized in neural architectures for structured and sequential data.
Building systems that forecast outcomes and surface insights from complex datasets. Particular experience with time-series and high-dimensional biological data.
Leading data science teams, setting technical direction, and bridging the gap between R&D and business stakeholders. Public speaking and workshop facilitation.
Deep experience applying AI to agriculture, food systems, and biological research. Understanding the unique constraints and opportunities in these sectors.
I'm always interested in discussing new challenges, especially where AI can create real impact in agri-food and beyond.
Get in Touch