AI Integration Engineer · 15+ years

I make AI work in production —
not just demos.

I build AI agents, RAG assistants, and custom MCP servers that connect to your real tools and data — plus edge-AI on ESP32. Full-stack engineer & CTO, working remotely with clients worldwide.

What I can build for you

From an idea to something that ships and keeps working.

AI Agents & Chatbots

Agents that use your tools and data (RAG, tool/function calling) — not just chat.

Custom MCP Servers

Connect Claude, Cursor, or your own AI to your APIs, databases and internal tools, securely.

AI Document Automation

Turn PDFs, scans and forms into clean structured data (OCR + LLM extraction + workflows).

Data + AI Systems

Pipelines, dashboards, extraction, matching and recommendation over your business data.

Edge-AI / IoT

Smart firmware on ESP32 (ESP-IDF / Arduino / TinyGo), with on-device AI.

Backend & Full-Stack

Production systems in Python/FastAPI, Go, and Next.js.

Selected projects

Real systems — with screenshots, code and live deployments. Live demos are password-protected; access available on request.

Compass — Procurement / Tender Intelligence

Turns a flood of public tenders into ranked, actionable opportunities.

An AI platform that crawls public procurement data, uses an LLM to extract and structure each notice, then matches and recommends opportunities to a company by capability — with match scores, risk flags, and a natural-language search. Full pipeline: crawlers → LLM extraction → pgvector matching → recommendation.

PythonFastAPICeleryPostgreSQL / pgvectorRedisNext.jsLiteLLM
Compass opportunity dashboard with AI match scores
Compass natural-language opportunity search Compass crawler data-source management with per-source scheduling
Capital-markets deal analytics — tranche composition report (mock data)

Capital-Markets Analytics & Reporting

Client project — designed and built a capital-markets research & reporting web platform to a financial-services client's requirements, plus a customized second deployment. Mock data only.

Next.jsFastAPIPostgreSQL
Janus multi-expert AI research council — tool calls with cited data sources

Janus — AI Research Agent (MCP)

Multi-tool AI research agent integrating four MCP tool services (market, macro, industry, news) with streaming responses and live data; fully deployable.

PythonFastAPIMCPAnthropic SDK
Phoenix document intake — OCR and extraction workflow states per document

Phoenix — Enterprise Document Processing

OCR + AI field extraction + rule validation + a workflow engine, with MCP integration. Go microservices + Next.js frontend.

GoNext.jsPostgreSQLMinIOMCPOCR
SealGuard — YOLO stamp detection with confidence score on a demo delivery note

SealGuard — Seal & Signature Verification

End-to-end document verification using computer vision (YOLO + Siamese-network embedding) with a backend pipeline and human-review workflow.

PythonFastAPIYOLONext.js
MCP Inspector connected to a Go Gmail-send MCP server — tool schema and protocol calls

Custom MCP Servers

Production-grade MCP servers (Go) connecting AI assistants (Claude, Cursor) to real tools via OAuth2 — minimal, secure, cross-platform.

GoModel Context ProtocolOAuth2
Muse — AI-extracted structured menu with live print-ready preview and human review

Muse — AI Conversation & Document Platform prototype

Turns messy requests from enterprise chat into structured data with LLM extraction + human review — then renders print-ready documents from templates. Phase-1 prototype.

PythonFastAPINext.jsLLM
Argus stock-analysis dashboard — daily AI market review in production

Argus — Stock Analysis Platform OSS customization

Restyled the React frontend, adapted the API, and containerized & deployed an open-source stock-analysis platform — running in production with daily AI market reviews.

ReactTypeScriptDocker

Built on the open-source ZhuLinsen/daily_stock_analysis — my work: frontend redesign, API adaptation, deployment.

About

I'm Yuexiang Yuan (Tom) — a full-stack engineer with 15+ years' experience and currently a CTO. I help businesses connect AI to their real systems: AI agents, RAG, and custom MCP servers that run in production. My background spans backend (Python / Go), DevOps, Web3, and embedded / edge-AI. I ship production-grade work with documentation, communicate clearly in writing, and offer ongoing support. Based in Nanjing, China — working remotely with clients worldwide.

Skills

AI / LLMAI agents · RAG · MCP · multi-model (Claude/GPT/Gemini/DeepSeek) · cost control
BackendPython · FastAPI · Go · Java · PostgreSQL · Redis · DuckDB
FrontendTypeScript · React · Next.js · Tailwind
Edge / EmbeddedESP32 · edge AI · IoT · embedded Linux
DevOpsDocker · Kubernetes · Jenkins
Web3Solidity · Ethers.js · Foundry · go-ethereum

Have an AI project that needs to actually ship?

Tell me what you're building and I'll tell you honestly if I'm a good fit.