Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View ong6's full-sized avatar
36 followers · 22 following

Achievements

Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx3Achievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx3Achievement: Quickdraw

Organizations

@NUS-Fintech-Society

Block or report ong6

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ong6/README.md

Hi, I'm Jun Xiong 👋

Software engineer in Singapore. I build AI infrastructure at TikTok by day and small tools by night, mostly to catch machines being confidently wrong.

  • 💼 AI Infrastructure Engineer at TikTok, Global E-commerce
  • 🛠 Currently building tools that make an agent prove what it says before anyone reads it
  • 🏢 Ran a one-person AI company on the side until a client bought it
  • 🎾 Away from the keyboard: tennis, a trading journal I actually keep, and a home server that always needs something
  • 💬 Ask me about agent runtimes, MCP, A2A, Go services, or why the ranking should never come from the model
  • 📫 junxiong.dev · LinkedIn · notes · email

Go TypeScript Python React Kubernetes Docker

GitHub contribution streak for ong6

How I build agent systems
Tools and data feed an agent runtime, whose output passes a deterministic ground plane before reaching an interface.

Pinned Loading

  1. sg-property-analysis sg-property-analysis Public

    Singapore condo decision system — URA transaction data, algorithmic scoring, and AI-agent qualitative research into one comparable score per property.

    Python

  2. groundplane groundplane Public

    Deterministic fact boundaries for agent output — fails the build when a model's structured output asserts something its tools never produced.

    Python