DevJams '24 — Divyakush Punjabi

Team lead of SYNTAX TERMINATOR — top 12 of more than 250 teams at GDSC DevJams 2024, with a voice-controlled home system built inside the window.DevJams is the flagship hackathon of Google Developer Student Clubs at VIT, and it draws the whole campus. More than 250 teams entered the 2024 edition, and SYNTAX TERMINATOR finished in the top twelve of them.Divyakush Punjabi led team SYNTAX TERMINATOR, four people, from brainstorming through build to the final pitch.What went in was a voice-controlled home automation system with no command grammar at all. The Google Gemini API resolves intent from open natural language, Python maps that intent onto actions, and those actions drive Arduino-controlled devices directly — with the Spotify API wired in alongside the hardware so playback is addressable by the same voice path rather than living in a separate app.Removing the fixed vocabulary is the whole point. A request works because it means something, not because it happened to be worded the way the system expects, which is what makes most voice control in the home feel brittle.Building it to a hackathon deadline set the scope. Everything that shipped had to work end to end on a table in front of a judge, which is a stricter test than a green build.

Selected work

Saturdays — Food Delivery Platform — A consumer food delivery platform — customer app, restaurant API, rider layer and operator console on one Django backend.
DineGuru — Restaurant POS and Billing System — A restaurant operating system — POS and GST billing, inventory, recipe costing, procurement and tiered analytics on one multi-tenant core.
GovernAI Research Atlas — Open-source platform unifying research papers, repositories and governance resources behind a single semantic vector index.
GovernAI Studio — Interactive training simulator for governance and compliance scenarios, backed by a RAG and LLM inference path.
Content Recommendation Engine — SASRec Sequential Recommender — Transformer-based sequential recommender with automated data pipelines, built as the IIT Ropar capstone project.
AI & IoT Rockfall Prediction — Geological Hazard Detection — Multi-sensor fusion pipeline for real-time geological hazard detection, running inference at the edge on live monitoring data.
Netra — AI Surveillance System — Autonomous person-tracking surveillance on constrained hardware, with real-time detection and an anomaly-scoring dashboard.
AlgoVerse — Data Structure and Algorithm Visualizer — Sorting, graph and tree operations rendered as animated 3D scenes, built to make data structures legible while they run.
IoT Smart Home Automation — Voice Controlled Home Assistant — Voice-activated home controller that interprets natural-language commands and drives devices directly, no fixed grammar.
Adaptive Traffic Light Controller — Verilog FPGA Design — Real-time traffic controller that adjusts signal timing to measured vehicle throughput, written in Verilog and synthesised to FPGA.

Record

National Entrepreneurship Challenge
Visionary Ventures
DevJams '24 — Vellore, Tamil Nadu
An AI major, read in parallel — Rupnagar, Punjab
Bharat’s leading startup summit — Surat, Gujarat
The calibre of the room — Surat, Gujarat
The first internship, signed off
Adaptive traffic control, in silicon
The day the submissions went in — Vellore, Tamil Nadu
Smart India Hackathon 2025
Convocation day at IIT Ropar — Rupnagar, Punjab
One with the grandmaster of computer science at IIT Ropar — Rupnagar, Punjab

Elsewhere

Divyakush Punjabi