Ahmedabad, Gujarat, India · UTC +5:30
I'm Kunj Shah, an AI engineer in Ahmedabad. I build AI agents, search over your own documents, full-stack AI apps and computer vision that runs on the device, for founders and small teams here and anywhere a repository can be shared.
Agents
An agent pipeline that compares every step against your app's real state before trusting it, and hands the task to a person when its confidence drops.
In the published Walkcast Lab run, 3 of 4 agent success claims were false. The harness flagged all three.
RAG
Search across your files that cites a source for every answer, scored against a set of real questions so you know the recall before launch.
EngineerOS runs a 20-question retrieval test in CI. If recall drops below its floor, the build fails.
Full Stack
Database, API, interface and deployment in one build, with backup model providers so one provider's outage never takes your product offline.
17+ systems shipped, including a multi-tenant CRM where a test fails the build if any query could read another customer's data.
Advisory
A read of where the spend goes, then a router that sends easy requests to small models and saves the large ones for hard reasoning.
Complexity-based routing cut API spend 65% and added under 200ms per request.
Computer Vision
Detection models quantized to INT8 and tuned for Jetson-class hardware, so inference runs on the device in under 100ms.
98.7% accuracy at 4.2x manual inspection speed on real railway track footage.
Kunj Shah is an AI engineer based in Ahmedabad, Gujarat (IST, UTC+5:30). He builds AI agents, document search (RAG), full-stack AI apps and edge computer vision for founders and small teams in Ahmedabad, across India, and remotely for clients abroad.
Kunj Shah quotes fixed-scope projects in INR after a free 15-minute call: ₹10,000–20,000 for a website with lead capture, ₹15,000–35,000 for an AI workflow automation, and ₹25,000–60,000+ for an AI product or MVP. Hourly work is ₹1,500/hour.
A fixed-scope build typically takes 2 to 4 weeks, from written scope to a deployed, tested product with a handoff doc. Payment is 40% upfront and 60% on delivery, with two rounds of revisions included.
Yes. Most work runs remotely: code goes into the client's own repository and cloud from the first commit, so location does not change how a project is delivered. Clients across India and abroad are welcome.
The client does. Everything lives in the client's repository, CI and cloud account from the first commit, with no platform or subscription to keep paying for.
Two or three sentences is enough: what it should do, who uses it, and when you need it. I reply within one working day.