{
  "id": 11951135,
  "title": "My friend was lost in the internship hunt, so I built him Get A Job.",
  "url": "https://urgent.news/2026/10/04/my-friend-was-lost-in-the-internship-hunt-so-i-built-him-get-a-job",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-04T15:29:48.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/notvats/my-friend-was-lost-in-the-internship-hunt-so-i-built-him-get-a-job-27l4"
  },
  "original_language": "en",
  "account": "This submission for the Hacktoberfest Weekend Challenge aims to create a useful tool for a friend, a third-year Computer Science student searching for summer and software internships. The friend wants opportunities at reputable companies, but finding them requires navigating various career pages, comparing locations and requirements, and determining which roles align with their resume. Entering similar information into multiple application forms is a tedious process. To simplify this, the developer built Get A Job, an internship discovery and application assistant that consolidates these steps into one platform. The project is an open-source AI internship discovery and application assistant. Users can upload their resume, review their profile, and find opportunities within their current country. Each search adds new listings to the dashboard, complete with location links, matched skills, and highlighted missing requirements. Application assistance fills out supported forms while allowing the user to review everything before submission.\n\nThe frontend of the application is built using Next.js, TypeScript, and Tailwind CSS, while the backend utilizes FastAPI, SQLAlchemy, PostgreSQL, and Alembic. For AI capabilities, the project employs Ollama with the Qwen3 8B model, which is run locally on the user's machine. This ensures that resume understanding, job requirement extraction, and answer drafts can be processed without sending sensitive data to external AI APIs. The AI provider can be easily replaced, providing flexibility without relying on proprietary services like OpenAI or GPT.\n\nThe project relies on Firecrawl for job discovery and public Greenhouse/Lever job APIs. PDF parsing and match scores are handled using deterministic code, with pypdf and Playwright assisting in resume extraction and form preparation, respectively. Validation and source evidence are incorporated to ensure accuracy, rather than blindly trusting the model's results. One key lesson learned during development is that valid JSON doesn't guarantee accurate information. Despite running the AI locally, the finished application benefits from the open innovation aspect, allowing users to process their resume directly on their device while still leveraging the internet for job discovery and applying to employers with reviewed information submitted through the platform.",
  "summary": "This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built I wanted to build something a friend could actually use beyond this weekend. My friend is a third-year Computer Science student looking for summer and software internships. He wants opportunities at good companies, but finding them means going through different career pages, checking locations and…",
  "key_points": [
    "\"Get A Job\" simplifies internship search and applications",
    "Open-source AI tool consolidates internship discovery and application process",
    "Local AI processing ensures data privacy and flexibility"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}