Document-to-JSON Pipeline for Academic CVs

The goal of this project is to build a robust two-stage pipeline that extracts clean text from academic CVs (PDF and DOCX) and transforms it into structured JSON using AI and large language models (LLMs). This project supports CtrlCV’s core functionality by allowing users to upload existing CVs and automatically populate their structured academic profile. The project combines two key objectives: Text Extraction – Accurately extract and clean raw text from uploaded CV documents, removing noise such as headers, footers, and formatting artifacts. AI-Based Structuring – Use prompt engineering and LLMs to classify and convert the extracted text into well-formed JSON objects that follow CtrlCV’s academic schema (e.g., sections like Education, Publications, Experience). The emphasis will be on reliability, maintainability, and future extensibility, including privacy-safe design and compatibility with downstream systems.

CtrlCV - Setup the Production Codebase

CtrlCV is transitioning from a Replit prototype to a robust production codebase, and your team will lay the groundwork for this transformation. The goal is to establish a clean, modular structure for both the frontend and backend, utilizing modern tools and best practices. This project will involve setting up local development and deployment workflows to streamline the process for future developers. By creating a solid foundation, you'll ensure that future contributors can easily understand and expand upon the codebase. This project offers a unique opportunity to apply classroom knowledge in software architecture, version control, and continuous integration, while working within a single academic program's skill set. The project is designed to be completed in under 80 hours, focusing on creating a maintainable and scalable codebase. You might be a good fit for this project if you : - Are comfortable with React, Node.js, and SQL - Have experience setting up local development environments - Are familiar with CI/CD pipelines and deployment platforms like Vercel, Railway, or Render - Want to build something that will be handed off to other developers - Care about code structure and developer experience What you'll do: - Set up a new GitHub repository with a clean folder structure (separate client/ and server/) - Scaffold the frontend using Vite + React + Tailwind CSS (or an equivalent tech stack) - Scaffold the backend using Express.js + Drizzle ORM + PostgreSQL (Neon) (or an equivalent tech stack) - Configure separate Neon databases (or branches) for development and production environments, with corresponding `.env` setup and switching logic - Ensure smooth local development: one-line setup (npm install and npm run dev) - Set up CI/CD pipelines using GitHub Actions, with deployments to:   - Vercel for frontend   - Neon for database - Add placeholder routes and pages as examples (e.g., /profile, /api/ping) - Include clear developer onboarding docs:   - README.md   - .env.example files   - Setup + deploy instructions - (Optional) Set up a seed script for test data - (Optional) Configure Prettier and ESLint for code formatting consistency