Deploy AI anywhere
exactly where you want
Want to use AI but worried where your data's going? We offer fully air-gapped deployments of multi-model AI applications on your own infra, via a single control plane across cloud and on-prem clusters.
Air-gapped Model Inference
Deploy open source and custom models with a few clicks in your own environment so it's data secure.
Compound AI Applications
Launch turnkey AI solutions like document query, data analysis, and meeting summarization. Mix different models and customize with your data - with all components hosted on your infra.
Control Plane for Hybrid Infra
Unify your infra across public clouds and on-prem resources. Monitor system health and activity, manage role-based access and resource allocation via a single interface.
A team on a mission to make infrastructure work for you
We're engineers who love solving hard problems in GPU orchestration. Our backgrounds span ML research, cloud architecture, GPU hardware, and robotics - but we're always learning from each other and the wider open source community.
Working across Singapore and India, our team brings together folks who've previously built large scale systems at companies like Meta, Nutanix, ByteDance, and Gojek. Many of us have spent substantial time in US and European tech ecosystems, and are now united back in Asia to build global tech from home.
We keep things simple: write good code, build reliable systems, and have fun doing it. If you're passionate about GPU infrastructure and enjoy diving deep into technical challenges, come join us!
