Resumai
Built an AI-powered resume–job matching system leveraging LLMs and embeddings to semantically analyze resumes and job descriptions. Developed a structured parsing and vector search pipeline to generate relevance scores and improve candidate–job alignment.
Problem Statement - Students and early professionals struggle to identify which job roles align with their skills due to unstructured resumes and complex job descriptions, leading to inefficient applications and poor role fit. At the same time, HR professionals face challenges in early-stage candidate screening, making it difficult to quickly identify the most relevant and high-potential candidates. This creates inefficiencies in the hiring process and increases the chances of overlooking suitable talent.
Proposed Solution - Develop an AI-powered resume analysis and job matching system that leverages LLMs and vector embeddings to semantically understand both resumes and job descriptions. The system extracts structured information (skills, experience, projects) and computes similarity scores to recommend the most relevant roles for candidates while highlighting gaps and improvements. For recruiters, the platform enables automated early-stage screening by ranking candidates based on relevance, generating explainable match scores, and filtering high-potential profiles. This reduces manual effort, improves hiring efficiency, and ensures better candidate–job alignment.
