Jet Chiang
Software Engineer, Solo.io
Toronto, Canada
Actions
Jet works on agentic infrastructure at Solo.io and he is a maintainer at Kagent, a CNCF Sandbox project for running AI agents on Kubernetes. He previously worked as undergraduate researcher in AI agent and ML for science at MIT and NUS. He enjoys reading literature and discussing philosophy.
Area of Expertise
Topics
Scaling AI Agents the Cloud Native Way with Kagent
Long gone are the days of chatbots. We’re now building autonomous agents that write code, manage infrastructure, and monitor environments. However, transitioning these agents from development to production requires solving critical challenges in security, governance, and observability. How do we apply a decade of Cloud Native experience to this new frontier?
This hands-on workshop introduces Kagent, a CNCF Sandbox project designed to orchestrate AI agents on Kubernetes. We will demystify the internal mechanics of agents and explore open standards — such as Agent2Agent (A2A) and Model Context Protocol (MCP) — that are foundational to the ecosystem. Participants will learn how to build AI agents to solve real-world problems and migrate existing agents to your Kubernetes environment with Kagent.
Secure, Stateful, and Serverless Agents on Kubernetes
Traditional Kubernetes pod-per-agent deployments fail at scale: running untrusted agents poses security risks, while idle agents waiting on LLM/MCP or user feedback waste massive cluster resources.
In this talk, we introduce Agent Substrate, an open-source runtime that achieves high-density agent multiplexing (up to 30x oversubscription) on Kubernetes. Substrate combines gVisor/microVM kernel-level sandboxing with sub-second suspend and resume capabilities, preserving full volatile RAM and filesystem state across hibernation cycles without overloading the K8s API server.
We will demo how Substrate rapidly hydrates and hibernates stateful agents, and show how Kagent layers on top, providing the control plane, abstractions, and UI required to orchestrate diverse harnesses (coding agents like Codex/Claude and framework agents like ADK/LangGraph) in a secure, serverless environment.
Kagent -- Bringing agentic AI to cloud native
Kagent is a CNCF sandbox project that enables DevOps and platform engineers to build, deploy, and run AI-powered workflows on Kubernetes. In this hands-on session, you’ll learn how to use Kagent to create agent groups that leverage subagents, tools, and MCP servers to act as intelligent DevOps assistants for your clusters. We’ll explore the core ideas that unite Kubernetes and agentic AI, then dive into building and deploying more complex agent workflows—whether declaratively via CRDs or from your favourite framework like LangGraph, ADK, and the OpenAI SDK.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top