LLM-powered full stack code analysis platform that detects bugs, security issues, and optimization opportunities using Google Gemini API. • Designed scalable MERN architecture with modular Node.js/Express backend and React frontend • Implemented Redis intelligent caching, reducing backend latency by 93% (19s → 1.3s) • Improved repeated response speed by up to 667% (20s → 30ms), significantly reducing LLM API cost • Built secure authentication, rate limiting, and file upload handling for production reliability • Integrated CI/CD deployment using Render Deploy Hooks for automated backend releases Tech: React, Node.js, Express.js, MongoDB, Redis, LLM APIs, CI/CD