Personal homepage China time

AI product engineer / multimodal systems

I code.

AI products, multimodal systems, and infra tuned until behavior becomes legible.

01 / Work

AI products, systems, infra.

From vague intent to shipped control surfaces.

HA Distributed services

Data Structured / unstructured

Infra Models / containers / tools

Lead/SRE Delivery / reliability

Product Scope / boundaries / shipping

Agents Search / reading / generation / structured output

Multimodal Image / voice / video / workflow

Ops Automation / remediation / containers

02 / Systems

Private work, reduced to surfaces.

Not all public. All treated as control surfaces.

Personal AI OS

Devices as interfaces

devices / voice / events / gateways

Knowledge engines

Memory as infrastructure

schemas / queues / graphs

Agent interfaces

Messy platforms, clean tools

CLI / MCP / agent I/O

Generative canvases

Pixels under direction

pixels / timelines / model control

03 / Art Direction

Art is a timeline you can scrub.

Motion, text, shade, and progress on one controlled axis.

frame.current = 000/144 0.00s / 6.00s

pixels.bind(bit)

ScrollVideo study

Scroll becomes time.

Frame, annotation, and exit state share one progress value.

<Timeline source="scroll" /> Map gesture to frame

<Control surface="pixel" /> Paint annotations

<Exit when="complete" /> Release the page flow

0% / 0.00s

04 / Shipped

Proof in products, not pitch decks.

PageOn

AI PPT generation with visual representation language and structured LLM output.

app.pageon.ai

Cyber Space

Multimodal AI chat on the App Store: text, voice, image, generation, conversion.

App Store

Tencent SRE systems

Automated operations, container optimization, SRE tooling, and alert remediation.

Automation operations / container optimization / SRE