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.
01 / Work
AI products with infrastructure underneath.
From vague intent to shipped control surfaces.
HA
Distributed services
Data
Structured / unstructured
Infra
Models / containers / tools
Lead/SRE
Delivery / reliability
Product
Scope / boundaries / delivery
LLM systems
Agent SDKs / Vercel AI SDK / Cloudflare AI Gateway / OpenAI Agents / Claude Code / Hermes
Generation
Stable Diffusion / LoRA / ComfyUI / GPT-SoVITS
Backend
FastAPI / Docker / model serving / internal tools
SRE
TDSQL / automation / containers / remediation
02 / Lab
Lab / private systems.
Small systems, tools, and experiments. Some private, some forked, all reworked into usable surfaces.
Memory as infrastructure
schemas / queues / graphs / retrievalMessy platforms, clean tools
CLI / MCP / browser / task I/OPixels under direction
image / voice / timeline / model control03 / Art Direction
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.
04 / Shipped
Proof in products, not pitch decks.
PageOn
AI PPT generation: visual representation language, structured LLM output, multimodal agents.
app.pageon.aiCyber Space
App Store multimodal AI chat: text, voice, image input, Stable Diffusion, voice conversion.
App StoreTencent SRE systems
TDSQL, Python ops packages, single-machine deploy, alert remediation, container optimization.
Automation / container optimization / SREPublic traces
Repos and images: forks, prototypes, containers, and model-service experiments.