Devices as interfaces
Phones, NFC, USB, voice, local events, message channels, and always-on gateways as one personal control plane.
devices / voice / events / gatewaysAI product engineer / multimodal systems
I code.
I turn vague product intent into controllable systems: pixels, prompts, data flows, services, deployments, and the tools that make teams move faster.
01 / Work
A builder for the messy middle of AI products.
I work where product judgment, model behavior, workflow design, and production engineering meet. The useful part is rarely one model; it is the system around it.
HA
Distributed, highly available services
Data
Structured and unstructured processing
Infra
Model serving, containers, internal tools
Lead/SRE
Delivery ownership and operations reliability
Product lead
Break down ambiguous AIGC needs, scope capability boundaries, and keep product, design, frontend, backend, and workflow teams moving together.
Agent systems
Build LangChain-based agents with search, reading, image generation, video retrieval, and structured output for stable frontend rendering.
Multimodal AI
Ship text, image, voice, and visual workflow systems using Stable Diffusion, LoRA, GPT-SoVITS, ComfyUI, FastAPI, Docker, and Gradio.
Infra / SRE
Turn repeated operations into reliable tools, from model-serving infrastructure to database operations automation, container optimization, and production remediation.
02 / Systems
Private lab work, grouped by control surface.
Some work starts from scratch; some starts as a fork, clone, or borrowed scaffold. I care about the control surface I can expose: what becomes observable, programmable, and reliable enough to use.
Memory as infrastructure
Persistent ingest, source traceability, schema-constrained extraction, graph relevance, and epistemic scoring.
schemas / queues / graphsMessy platforms, clean tools
Real-world surfaces wrapped as CLI, MCP, skills, JSON-first contracts, and safety rails that agents can actually use.
CLI / MCP / agent I/OPixels under direction
Whiteboards, timelines, scene protocols, TTS, animation, GPU scheduling, and model behavior control.
pixels / timelines / model control03 / Shipped
Proof in products, not pitch decks.
Creamoda
AI fashion design tools with ComfyUI workflows, distributed data collection, visual-language labeling, and internal efficiency systems.
AI fashion workflow shippedPageOn
AI PPT generation with a visual representation language, structured LLM output, and agents that compose multimodal presentation content.
app.pageon.aiCyber Space
Multimodal AI chat product on the App Store, combining text, voice, image input, Stable Diffusion generation, and voice conversion services.
App StoreTencent SRE systems
Automated operations, container optimization, and SRE tooling for TDSQL: faster single-machine deployments, reusable Python ops packages, and alert remediation at scale.
Automation operations / container optimization / SRE04 / Principles
Every pixel and every bit is controllable.
To me, "I code." is not just writing programs. It is taking responsibility for the full behavior of a system. Pixels carry intent. Bits carry state. Code is how both become observable, adjustable, and reliable enough to ship.