Vaibhav Bhandari
I build and study intelligent systems that have to work in the real world.
Founding engineer, Mapsense → Apple (2015) · ten years scaling ML systems at Apple Maps · now independent, in Indore
Today I research and advise on making probabilistic AI dependable in real operations — automation at enterprise scale, small and local models at the edge, and geospatial intelligence.
Now
- Acropolis Edge Lab — I direct two student teams investigating offline voice and vision, with weekly reviews at Acropolis. First cohort: October 2026.
- Latest note: Small AI And Small Talk
Work with me
Have a concrete question about making AI reliable in a real workflow, or running it under device and connectivity constraints? I welcome technical conversations and selectively scoped advisory or paid feasibility work.
Also running
Long-running systems and personal instruments.
Knos Digest
A personalized, high-signal daily digest of tech news.
AI chatbots give wrong answers to financial queries 'most of the time'
1 story · AI/ML/LLMs
State Overflow
A data scientist's lens into everyday decisions.
The $80 Hike In Vietnam That Changed How I Think About Vacations
Understanding tourist traps through statistics
May 2026Metrics Dashboard
Observing daily habits without a productivity app.
Last week
Routine score = 0–4 based on daily habits (family, fitness, sleep, work).
Reading
A few books I keep returning to:
Steve Jobs
Sapiens
The Fountainhead
The Sirens of Titan
The Mind Illuminated