Personal homepage China time

AI product engineer / multimodal mapping

input text

i map(x)

text -> image
output image

Text, image, audio, logs, scenes, and traffic mapped into controllable products, code, state, and operations.

AI products with production-grade systems.

Hands-on across product interfaces, agent runtimes, cloud platforms, model serving, data pipelines, and SRE automation.

Product Interfaces / scope / delivery
Agents Tools / runtimes / evaluation
Cloud Cloudflare / Vercel / Google Cloud
SRE Automation / reliability
Product systems Turn ambiguous intent into scoped interfaces, workflows, and shipped tools
AI & agents Agent SDKs, tool use, evaluations, generation pipelines, model control
Cloud & backend Cloudflare, Vercel, Google Cloud, FastAPI, Docker, model serving
Data & SRE Structured/unstructured pipelines, TDSQL ops, container optimization, remediation

Systems as interfaces.

Agents, memory, devices, and generative media shaped into usable tools.

Personal AI OS

Devices as interfaces

devices / voice / events / gateways
Knowledge engines

Memory as infrastructure

schemas / queues / graphs / retrieval
Agent interfaces

Messy platforms, clean tools

CLI / MCP / browser / task I/O
Generative canvases

Pixels under direction

image / voice / timeline / model control

Art is a timeline you can scrub.

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

ScrollVideo study

Scroll becomes time.

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

0% / 0.00s

Proof in products, not pitch decks.

PageOn

AI PPT generation: visual representation language, structured LLM output, multimodal agents.

app.pageon.ai

Cyber Space

App Store multimodal AI chat: text, voice, image input, Stable Diffusion, voice conversion.

App Store

Tencent SRE systems

TDSQL, Python ops packages, single-machine deploy, alert remediation, container optimization.

Automation / container optimization / SRE

Public traces

Repos and images: forks, prototypes, containers, and model-service experiments.