A college student from Mainland China.
Undergraduate @ UESTC ยท Biomedical Engineering (Software Engineering)
| Period | Role | Company |
|---|---|---|
| ๐ญ 05/25 โ 09/25 | Digital Industries Software Engineer Intern | Siemens DISW |
| ๐ช 12/25 โ 04/26 | WeChat Cross-Platform Development Intern | Tencent WXG |
| ๐ค 04/26 โ Present | WeChat AI Agent Development Intern | Tencent WXG |
AI Agent - Active
- ๐ค Agent Pipeline Engineering โ building Function Call toolchains and agent dispatch strategies inside WeChat
- ๐จ Real-time UI Rendering โ Markdown rendering engine and chat UI components for AI assistant interfaces
- ๐ง MCP Tooling โ learning Model Context Protocol, tool registration, and agentic workflow patterns
- โก Agentic System Design โ model scheduling, context management, reactive UI via MCP-driven state
๐ง RainCppAI
C++17 AI Application Service Platform โ self-built HTTP framework, production-grade pipelines
-
Self-authored HTTP framework โ Reactor model (muduo), state-machine parser, middleware chain, dual-path routing
-
Standard MCP Server โ JSON-RPC 2.0
tools/list+tools/call, directly connectable to Claude Desktop / Cursor -
Multi-strategy LLM routing โ Factory + Strategy pattern, hot-swap between Qwen / Doubao / RAG / MCP
-
SSE streaming output โ curl callback token-by-token push, zero-wait frontend rendering
-
RAG pipeline โ Alibaba Bailian knowledge base integration + retrieval-augmented generation
-
Async architecture โ AI calls offloaded to 8-thread pool, IO threads non-blocking;
shared_mutexLRU (500 sessions max) -
ONNX Runtime inference โ MobileNetV2 image recognition with OpenCV preprocessing
-
RabbitMQ + MySQL โ async decoupled message persistence
โก RainHTTP
Lightweight C++ HTTP server framework built from scratch
- Reactor event-driven model with epoll multiplexing
- Stateful HTTP/1.1 request parser + routing engine
- Middleware pipeline, session management, SSL/TLS support
๐๏ธ RainKVRaftCpp
Distributed KV storage with Raft consensus, implemented in C++
- Full Raft leader election + log replication + persistence
- Linearizable reads and fault-tolerant writes across cluster nodes
- Built to understand the engineering gap between theory and production consensus
๐ AI_Learning (Active)
Notes & practice projects from learning the AI engineering stack
- Covers: Agent architecture, LLM API integration, RAG pipelines, MCP tooling
- Ongoing โ updated alongside internship at WeChat AI Agent team
๐ Engineering Snapshot
๐ซ Contact Me
- ๐ง rainrain45032@gmail.com
- ๐ github.com/Rain0832
- ๐ฌ WeChat Official Account: ไบCoding
"Build things that scale. Understand what you ship. Make AI actually work."

