I build, break, and benchmark AI systems for a living.
As a Data Science and Machine Learning Engineer at Abundant AI, I specialize in AI evaluation, pushing models beyond surface level performance to uncover how they truly behave in the real world. I design rigorous evaluation frameworks, stress test models for robustness, and turn messy, complex data into clear, actionable insights.
I’m driven by one goal: making AI not just smarter, but reliable, accountable, and production ready. I thrive in high impact environments where precision matters and assumptions get challenged. If it can’t be measured, it can’t be trusted, and I make sure it is.
