OpenRelay
Building the brand, product, and developer experience for a distributed AI inference platform.
- Role
- Product Design Engineer
- Status
- Actively in development
- Technologies
- FigmaNext.jsReactTypeScriptTailwind CSSFramer Motion
Overview
One API for distributed inference.
OpenRelay runs production AI workloads across a distributed GPU network through a single, OpenAI-compatible API.
The Challenge
Most platforms expose the complexity.
Running inference across GPU providers means different APIs, pricing, regions, and capacity that never sits still. OpenRelay abstracts all of it into one endpoint.

Areas of Ownership
From brand to frontend.
Product
Dashboard, inference playground, VM provisioning, and onboarding. The dashboard leads with health, performance, and spend. Drag to compare.






