Focused on RAG, agent, and backend application development, with Python backend practice and Java development experience in an enterprise environment. Able to deliver knowledge bases, agent workflows, backend APIs, data storage, and containerized deployments while using AI coding agents to improve cross-stack development efficiency.
Showcasing impactful projects and technical achievements.
A RAG / Agent application built from public BYD Qin, Song, and Han vehicle manuals and charging-safety materials, combining vehicle knowledge Q&A, personal charging-data analysis, and initial charging-fault screening.
A Reactive Network cross-chain risk protection system that turns an origin-chain risk signal into an automated destination-chain action.
ChainCashier is a cross-chain checkout agent for Web3 merchants: merchants lock the destination chain and exact USDC amount, payers can pay from another supported chain, and LI.FI aggregates and validates the cross-chain route.
A BOT Chain Testnet commitment DApp combining on-chain wake-up check-ins with AI coaching grounded in real challenge history.
Work experience and enterprise internship experience.
Contributed to million-level fixed-asset valuation projects by conducting on-site inspections, collecting data, verifying information, and organizing appraisal materials to support report drafting.
Contributed to backend development for a public-opinion analysis system, 99Bill payment integration, and a CRM system, including business-logic analysis, feature development, code debugging, and API integration.
Core capabilities across RAG, agents, Python backend development, enterprise Java development, and cross-stack engineering.
Builds RAG / Agent applications with Python, LangChain, and LangGraph, covering PDF / HTML parsing, text chunking, embeddings, Chroma, hybrid BM25 and vector retrieval, RRF, and citations. Uses LLMs for structured query planning and improves recall through source grouping, candidate quotas, and backfilling, with versioned Hit@K and MRR evaluation and Cross-Encoder reranking comparisons. Experienced with tool calling, structured output, context management, Redis caching, fallback handling, and safety controls before and after model calls.
Extensive experience using AI coding agents including Codex and Cursor to organize cross-stack development, troubleshooting, documentation, and deployment verification through requirement decomposition, project rules, staged implementation, and testing and acceptance. Has used DeepSeek, GLM, GPT, and related APIs, with hands-on experience deploying Hermes Agent, integrating instant messaging, monitoring markets, running simulated trades, and connecting live-trading APIs.
Has Java development experience at TRS and Spring Boot project experience using Spring Cloud, MySQL, Redis, and RESTful APIs. Contributed to public-opinion data processing and filtering, completed the full 99Bill payment integration flow, and worked on CRM access isolation, data management, and API integration with Spring Boot, MySQL, and Redis. Can use AI Coding to quickly understand existing Java codebases and deliver requirements, APIs, debugging, and features.
Hands-on experience developing Solidity smart contracts and DApps with React, Next.js, and TypeScript, using Foundry / Hardhat for contract development and testing and RainbowKit, Wagmi, and Viem for wallet integration, contract reads and writes, and transaction signing. Deployed and launched multiple DApps and won first prize at the Reactive Network AI Hackathon with FlashBack. Passed CET-6 and can comfortably read English technical documentation.