Xunzhuo
Liu

Building the Mixture-of-Models for the next era of computing.

Discover
Latest Thesis

The Semantic Routing Moment

The next era of AI will not run on one model. It will run on a Mixture-of-Models—and semantic routing is the decision layer that makes it work.

A preference-aligned Mixture-of-Models presents one stable contract across changing models, hardware, and locations. The user chooses the preference—speed, cost, balance, or accuracy—and the system decides how to realize it.

vLLM Semantic Router is the open decision layer we are building for that future.

Work 01

vLLM Semantic Router

Co-Founder

An open semantic decision layer for preference-aligned Mixture-of-Models.

Work 02

Elephant Agent

Creator

Personal-model-first self-evolving AI agent that grows correctable understanding and gets curious at the user's pace.

Work 03

Inferoa

Builder

Inference-native tokenmaxxing agent harness for loop engineering.

Work 04

Envoy Gateway

Steering Committee and Maintainer

Manages Envoy Proxy as a standalone or Kubernetes-based application gateway.

Work 05

Envoy AI Gateway

Maintainer

Manages unified access to generative AI services built on Envoy Gateway.

Role 01

Agentic Intelligence Lab

Chair

Chairing the lab's research and community work on agentic AI, personal AI agents, and system intelligence.

Role 02

Kubernetes AI Gateway WorkGroup

Co-Chair

Leading the community effort to define standards for AI Gateway in the Kubernetes ecosystem.

Role 03

CNCF Ambassador

Fall 2023 Ambassador

Representing and promoting Cloud Native Computing Foundation projects and values globally.

Role 04

Linux Foundation APAC Open Source Evangelist

2024 Program

Advocating for open source adoption and best practices across the Asia-Pacific region.

Role 05

KubeCon Program Committee

KubeCon 2024 Hong Kong

Reviewing and selecting talks for one of the largest cloud-native conferences.