
2
1
India
1 year of experience
I'm Divyansh Kumar, a B.Tech student in Artificial Intelligence & Data Science from India with a strong interest in AI, machine learning, Python, and software development. I enjoy building practical projects, participating in hackathons and coding competitions, and continuously improving my technical skills. My goal is to develop AI-powered solutions that solve real-world problems while growing as a software engineer and AI developer.

Nigeria's informal sellers including online vendors, market traders, side-hustlers, can't get buyers to pay upfront, because there's no shared trust layer between strangers. Nearly every transaction defaults to cash on delivery, and a single refused delivery erases days of margin for a seller who can least absorb it. FairPrice fixes this without asking sellers to leave the tools they already use. A seller generates a payment QR or link from a dashboard or directly inside WhatsApp. The customer pays, funds are held in escrow, and they release the moment delivery is confirmed, no trust required on either side. Behind this sits ZEMA 360, our autonomous commerce agent layer. Its core AI flows, product listing generation, price intelligence, and the Ziva customer assistant, run on Qwen 3.7 Plus (Alibaba), served through Fireworks AI on AMD Instinct GPUs, as the primary inference path in production. This is orchestrated with UiPath Maestro for fulfillment workflows and human-in-the-loop approval on high-value payouts over WhatsApp, with zero human operator watching every transaction. This isn't infrastructure built for a hackathon demo, it's running in production right now, processing real payments for real Nigerian sellers, since before this hackathon started. We're live since May 2026, before any paid acquisition: over a dozen active sellers, 1k+ real users, real orders, and real GMV moving through escrow, on AMD-hosted inference doing the actual work of pricing and fulfillment, not just decorating a README.
13 Jul 2026