About

I'm Sara, an ML engineer who builds and evaluates AI systems. I'm most interested in the unglamorous middle of the work: figuring out when a model fails, finding a way to measure that failure honestly, and improving reliability without quietly trading away performance.

That focus has taken me across recommender systems, LLM evaluation, and computer vision, usually with a fairness or bias question at the center.

Outside of work you'll usually find me in the garden. Lately I'm growing cut flowers and loofahs (yes, the sponge kind, they start life as a gourd). Turns out the job is much the same either way: set up the right conditions, watch closely, and pay attention to what the results are actually telling you.