top of page
For Dark BG.png
< Back

Resume Screener & Fit Analyzer

Project Overview

Type: Personal Project
Tech Stack: Python, Streamlit, OpenAI GPT, PyMuPDF
Role: End-to-end builder (ideation, development, deployment)
Timeline: 1-week prototype

Summary

Resume Screener & Fit Analyzer is a web application that allows recruiters to upload a resume and job description to instantly evaluate fit using OpenAI’s GPT models. The tool generates a Fit Score (0–100), highlights matched and missing skills, and provides a concise AI-generated recommendation to support decision-making. Built with Streamlit for an interactive UI and PyMuPDF for PDF parsing, the tool streamlines the resume screening process—saving time, reducing bias, and improving consistency across hiring pipelines.

Problem Statement:

Recruiters and hiring managers often receive hundreds of resumes per role, making it time-consuming and inconsistent to manually evaluate each one. Matching a resume to a job description requires careful analysis of skills, experiences, and context—leading to inefficiencies, missed talent, or biased shortlisting decisions.

Solution: 

This tool enables users to:

  • Upload a resume (PDF) and corresponding job description (text)

  • Automatically extract:
    A Fit Score between 0–100 based on semantic skill match
    Key skills that match the job description
    Missing skills or gaps in experience
    A brief recommendation to support shortlisting decisions

  • Speed up screening by providing structured, AI-generated insights

  • Built with Streamlit, it offers an intuitive interface without requiring technical knowledge

How It Works:

  1. Upload a resume and job description via the web interface

  2. The backend uses PyMuPDF to parse the resume PDF and OpenAI GPT to analyze the content

  3. The app displays:

  4. A Fit Score

  5. Matched and missing skills

  6. An AI-generated summary recommendation

  7. Results are formatted and displayed in a clean, readable layout for recruiters

  8. API keys are securely handled using environment variables (.env or Streamlit secrets)

Tools and Techniques

  • OpenAI GPT: Natural language processing and structured output generation

  • Streamlit: Interactive frontend UI and app deployment

  • Python: Backend logic, file handling, API integration

  • Notion API: Task assignment and database management

  • Environment Variables: Secure API key configuration

Key Learnings

  • Designing end-to-end AI-powered applications

  • Parsing and structuring complex, unstructured text data

  • Ensuring seamless multi-API integration (OpenAI + Notion)

  • Managing user experience to maintain context across asynchronous steps

  • Handling real-world issues like date parsing, error handling, and state management

Real Life Use Cases

  • Product and project managers summarizing meetings

  • Customer success teams capturing client discussions

  • Executive assistants preparing follow-up notes

  • Teachers and facilitators generating summaries of learning sessions

  • Government offices automating task tracking from inter-departmental meetings

Try the live demo

Image by hesam Link

Key Outcomes / Results:

  • Designing end-to-end AI-powered applications

  • Parsing and structuring complex, unstructured text data

  • Ensuring seamless multi-API integration (OpenAI + Notion)

  • Managing user experience to maintain context across asynchronous steps

  • Handling real-world issues like date parsing, error handling, and state management

bottom of page