Profile image for Jashwanth Peddisetty

Jashwanth Peddisetty

I am a developer and indie hacker who loves building products at the intersection of creativity, art, and technology. I enjoy participating in hackathons and creating cool products that solve real problems.

I am currently working on OpenGen, an AI-powered reel and podcast generation application, and another kids' DIY toy-making company named ARTLY (two vastly different domains that allow me to explore both cutting-edge technology and hands-on creativity both important to make life beautiful 😉). My current focus is primarily in the fields of text-to-video (txt2vid) and text-to-image (txt2img).

I actively share my work and build in public on X (formerly Twitter). This is my first time writing blogs as a way to reach a larger audience.

All posts by Jashwanth

How to connect Convex to RunPod for serverless GPU workloads
Every GPU task I've run from a backend has the same problem: you fire off the job, then poll for results or wire up webhooks to know when it's done. This walkthrough shows a different approach. Convex triggers a GPU job on RunPod, and the RunPod worker calls mutations directly on Convex using the Python client. The frontend stays in sync through live queries. No polling, no webhook infrastructure. I'll walk through the full implementation using video background removal as the example, but the pattern works for any GPU workload — compression, transcription, object detection, whatever you need.
Matrix: Building a real-time RPG game with Convex
Matrix is a real-time RPG for language learning, using Convex for live updates and AI for translations. Players chat with nearby users on a shared map, leveraging a simple Convex backend for real-time interactions.