Meet Our Team
OUR STORY
We started Embedded LLM with a simple goal: make AI practical, fast, and accessible to everyone.
Frustrated by the complexity and cost of deploying large language models, we built JamAI Base—a no-code platform that lets businesses embed LLMs into their workflows in minutes, not months.
Born in Singapore and Kuala Lumpur, our team is redefining how AI is built and used—locally, securely, and efficiently. We’re also growing a community of builders through events like vLLM Asia Developer Day, pushing the edge of what’s possible.
AI shouldn’t be distant. That’s why we’re embedding it.
Vision
vLLM everywhere: the fastest engine on any hardware, powering an interoperable, federated AI utility.
Mission
A federated AI utility powered by vLLM: fastest on any hardware, interoperable by design, and aligned with the ecosystem so contributors and partners all benefit.
OUR TEAM
Our Advisory Board
Barbara Meynert