About me

Hi! I'm Philipp — a Senior Applied Scientist at StreetEasy, where I work full-stack across several projects: our home value estimate, matching, and recommendation — from the data and the models through to the services and APIs that ship them.

Nine years on the same domain, which is long enough to see things through. The valuation model covers about 1.5 million New York homes; the entity matching behind comps and market reports runs daily; the API serving both handles a few thousand requests a minute. Most of what I've learned lives in the gap between a model that works in a notebook and one that works on a Tuesday morning.

I'm drawn to tools and services somehow connected to the physical world. I got here the long way around — first an architect, then an urban planner, then a data journalist, and now — applied scientist. I've long stopped treating those as separate careers — it's one way of working that's just had several names.

Before moving to NYC, I co-created Branchpoint, a non-profit teaching parametric design project, and perhaps one day I'll get back to it. And I teach at both university and school level.

I write here now and then — most recently on packaging a research algorithm so strangers can install it and on what changes when your notes' heaviest readers are agents. The full list has the papers, talks, and older work.