Developed an AI-powered resume analysis platform using Python and Flask to evaluate resumes against job descriptions and provide semantic matching insights. Integrated RoBERTa-based sentence transformers to generate contextual embeddings and compute similarity scores between resumes and job descriptions. Implemented automated PDF text extraction using PyMuPDF, followed by preprocessing and structured information extraction for downstream analysis. Built a resume scoring engine that evaluates resumes based on skills, experience, education, and semantic relevance to job requirements. Designed an interactive web interface for resume upload, analysis, and visualization of match scores and improvement recommendations. Optimized inference performance through efficient text preprocessing and embedding generation, reducing analysis latency for uploaded resumes. Structured the application using a modular Flask architecture with separate components for document processing, embedding generation, scoring, and API