Hi, I'm Vaibhav

0 → 1

I was involved with Mapsense from before the company formally existed, joined full-time at seed as a founding engineer, and helped build the core product through its acquisition by Apple about two years later. That experience set my defaults: small team, direct ownership, product clarity, and the particular joy of watching something exist that didn't before.

Scale

Then roughly ten years at Apple Maps — ML systems, large-scale data infrastructure, geospatial systems, aerial imagery, production pipelines across 20+ countries. In my final year I designed the architecture for an internal agentic platform, and learned the lesson that now shapes my research: agents expose the debt a system already carries — fragmented data, knowledge living in people's heads, workflows that exist nowhere in machine-readable form. Real systems care about determinism, consistency, reproducibility, and reliability, and probabilistic components don't get a pass on any of it.

I also learned something about myself: I'm energized by architecture, research, experimentation, and small teams — and much less by large-scale organizational alignment. That difference is a big part of what I'm doing now.

Back to 0 → 1

I left Apple in 2026 and moved to Indore. What I'm doing now is not a change of subject — it's the same question I kept running into at Apple, taken up without an organization in the way: how probabilistic AI becomes dependable in real systems, especially when it has to run local, offline, and small. The Acropolis Edge Lab — a student research cohort here — is where that question gets built and measured on actual devices.

The geography is deliberate. Indore is for depth: synthesis, building, long uninterrupted mornings. Bangalore is for collision — periodic, deliberate immersion in a dense ecosystem to expose the work to people and come back with better questions. The first thing that trip produced is Small AI, Real Systems.

Reading

Reading is an input to the research, not a shelf. Currently working through Richard McElreath's Statistical Rethinking — slowly, and deliberately. All-time favorites live on the homepage; more on Goodreads.

Working together

I'm not looking for a full-time role. I am looking for a small number of specific conversations: researchers and builders working on dependable AI, small models, edge systems, or geospatial and physical intelligence; founders and technical leaders who want a hard second opinion on an AI systems architecture; and universities or communities running applied research programs. Trained in operations research at Columbia, if you want the formal version: resume.

What I'm useful for →

Say hello or book a time.