At PeopleSense.AI, I own PeopleSense HeatMap, a live map of sensor occupancy and earthquake and public-safety alerts. I led platform and security changes, replacing direct browser access to DynamoDB with an authenticated TypeScript API on Postgres/PostGIS.
I built a Rust service for USGS ShakeAlert and streamed earthquakes live to signed-in users over authenticated, per-tenant WebSockets. The product also delivers on-device geofenced warnings, with a countdown to when shaking arrives.
I delivered a permanent PeopleSense micro-cell at Rajiv Chowk, Delhi Metro, and ran machine-learning models on transit data that improved inference accuracy by 27%. I also mentor student cohorts on Python, Raspberry Pi, MQTT, AWS, and AI-assisted coding.
At Glocol Networks, I took PeopleSense Monitor from a practice-school prototype to a multi-tenant production dashboard for 11+ client organisations. I also rebuilt sensor auto-deployment for the Greengrass migration and deployed and maintained more than 100 IoT sensors.
