Shidong L.Private profile: Upwork shows its earnings only to signed-in members, so we check it every few weeks, not daily. MRR here is a rough estimate (Upwork's six-month earnings ÷ months active). Last read Nov 5, 2026.

I’m a full-stack engineer focused on building production-ready AI applications, AI agents, and scalable web systems. I work mainly with Python, LLMs, FastAPI, React, and modern cloud architectures — helping businesses turn AI ideas into reliable products and automation workflows. AI / LLM Engineering • AI agents & agentic workflows • LLM integration — OpenAI, Claude, Gemini, DeepSeek • RAG / enterprise knowledge bases / semantic search • Tool calling & structured outputs • MCP integrations • ReAct & multi-step workflows • Multi-agent orchestration • Context & prompt engineering • Human-in-the-loop AI workflows • LLM evaluation & reliability • Document extraction, OCR & classification Backend & Systems • Python — FastAPI, Django, Flask • REST APIs & asynchronous services • PostgreSQL, MySQL, Redis • SQLAlchemy & Django ORM • Microservices & distributed systems • Cloud-native architecture • Third-party API integrations • Data processing & automation Frontend • React / Next.js • Vue • Tailwind CSS • AI-powered dashboards and workflow applications What I Build • AI agents and business automation • Enterprise AI assistants • RAG / private knowledge-base systems • AI document processing & data extraction • LLM-powered SaaS products • AI-enabled internal tools • Data and workflow automation • Full-stack MVPs and production systems How I Work I focus on practical AI engineering rather than adding AI simply because it is fashionable. My approach is straightforward: Understand the workflow → design the architecture → integrate AI where it adds real value → validate the output → keep humans in control where necessary → ship. You can expect clear communication, pragmatic technical decisions, clean code, and fast iteration without sacrificing maintainability.