Skip to content
View Chengyuli33's full-sized avatar

Highlights

  • Pro

Block or report Chengyuli33

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Chengyuli33/README.md

👋 Hi, I’m Chengyu!

I'm a full-stack software engineer combining a background in marketing analytics with a Master's in Computer Science at the University of Pennsylvania. The journey has given me a rare mix of user insight, data architecture, and technical precision.

Since graduating, I've built full-stack applications that integrate search, information retrieval, and LLM-powered features. My work spans the entire stack: from designing databases and data pipelines to building APIs and frontend development.

I recently completed ✨Reading Bee, my own AI-powered book recommendation platform that integrates RAG pipelines, FAISS vector search, and semantic embeddings on a FastAPI + PostgreSQL backend.

Currently working on an AI agent-driven NPC simulation platform, combining game design and generative AI, creating dynamic, human-like character interactions. 👉 About this Project

⚙️ Current Skills

  • Languages: Python · JavaScript · TypeScript · Java · SQL · Bash
  • Web & APIs: FastAPI · React · Node.js · Express · HTML/CSS · RESTful APIs · Neo4j
  • Data & ML: PostgreSQL · pgvector · Scikit-learn · FAISS · Pandas · NLP · Feature Engineering · Data Visualization
  • DevOps & Cloud: Docker · Kubernetes (K3s) · ArgoCD · Nginx · AWS RDS · CI/CD · GitHub Actions
  • Tools & Workflow: Git · Vim · VS Code · Postman · Jupyter Notebook · Figma · Linux Shell · DataGrip
  • AI & Systems: OpenAI · Claude · Ollama · Semantic Search · Vector DB · Retrieval-Augmented Generation (RAG) · Model Context Protocol (MCP)

🌱 Let’s Connect

  • 📍 Based in New York, NY
  • 💼 Reach me on LinkedIn

✨ The world is your oyster, and the future is ours to design. ✨

Pinned Loading

  1. reading-bee reading-bee Public

    📚 A full-stack book recommendation platform featuring Retrieval-Augmented Generation (RAG), a conversational AI chatbot (Ollama), and LLM tool-calling for semantic retrieval, personalized search, a…

    Python 1

  2. spotify-web-music-explorer spotify-web-music-explorer Public

    🎧 A full-stack music search and analytics platform built with React, Node.js, PostgreSQL, and AWS RDS. Features advanced filtering, interactive visualizations, and RESTful APIs for exploring songs …

    JavaScript 1

  3. nutriScore-analyzer nutriScore-analyzer Public

    🍔 End-to-end ML pipeline analyzing 173K+ U.S. packaged foods (163 features): data cleaning → EDA → PCA/UMAP clustering → Nutri-Score classification, with model interpretability and insights.

    Jupyter Notebook

  4. biography-parser-text-generation biography-parser-text-generation Public

    ✍️ Fine-tuned NLP system for Wiki bio parsing and sci-fi story generation, featuring text generation, structured data extraction, multi-attribute evaluation (60+ fields), cost–performance trade-off…

    Jupyter Notebook

  5. imdb-openflights-database-project imdb-openflights-database-project Public

    🛫 Cloud-based SQL project analyzing IMDB and OpenFlights datasets. Designed normalized relational database schemas, implemented analytical joins and CTE queries, and deployed PostgreSQL on AWS RDS …

  6. mcp-weather-server-demo mcp-weather-server-demo Public

    🌦️ A lightweight MCP (Model Context Protocol) server demo built in Python for Claude Desktop integration. Implements real-time weather retrieval tools built with FastMCP and httpx and the National …

    Python