A personal notebook on applied machine learning, systems engineering, and the small details that turn a promising model into something people actually use.
Long-form thoughts on building intelligent systems — the wins, the failures, and everything in between.
A selection of tools and experiments, mostly born from a need that didn't have a good answer yet.
I'm an independent researcher and software engineer fascinated by what happens when intelligent systems meet the real world. I care about the unglamorous parts: latency budgets, data pipelines, evaluation harnesses, and the hundred small decisions that separate a demo from a product.
These pages are where I think out loud. If something here is useful, or wrong, or both — I'd love to hear about it.
Start a conversation →Open to interesting problems, collaborations, and good conversations about technology.
Say hello →