platoseedplatoseed
The first AI agent for optimizing ML model inference on edge hardware
RunLocal is the first AI-native platform for optimizing ML model inference on edge hardware (like Nvidia Orin and Qualcomm) Our AI agent automates on-device model performance debugging and optimization. Our web platform replaces brittle validation scripts and manual experiment tracking. With RunLocal, you deploy more capable/efficient models on your target hardware with a fraction of the engineering effort. We’re working with market-leaders in autonomous vehicles, robotics, drones and smart cameras. We're backed by investors like Y Combinator and 468 Capital.
Co-Founder & CEO of RunLocal AI Building the first AI agent for optimizing ML model inference on edge hardware (like Nvidia Orin and Qualcomm) → www.runlocal.ai Previously worked on the first edge AI video codec at Deep Render and AR/VR apps at Meta.
CTO of Neuralize. Previously a software engineer at Marshall Wace (Europe's largest hedge fund) building an internal AI platform for developers and optimizing low latency streaming systems.
Formerly “Neuralize” · why startups rename →
The default way of running on-device AI at Scale
Enabling Model-Hardware Co-Design at Scale
