MadsLorentzen/ai-job-search

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

What it solves

Applying for jobs is often a tedious process of manually tailoring CVs and cover letters for every single application. This project provides an AI-powered framework to automate the search, evaluation, and application process while ensuring the final documents are professional, tailored, and visually perfect.

How it works

The system turns Claude Code (a CLI agent) into a full-stack job application assistant. It uses a structured workflow consisting of several key stages:

  1. Profiling: The user sets up a personal profile by importing existing CVs, LinkedIn exports, or through an AI-led interview.
  2. Searching: It uses specialized CLI tools (built with Bun) to scrape job portals for matches and ranks them based on a fit-scoring framework.
  3. Application: For a chosen job, the system runs a "drafter-reviewer" pipeline. It drafts a tailored CV and cover letter in LaTeX, spawns a second agent to critique the drafts, and revises them.
  4. Verification: The system compiles the LaTeX into PDFs and visually inspects the layout to fix orphans or page spills. It also performs an ATS-check by extracting text from the PDF to ensure it is machine-readable.
  5. Management: It includes tools to prepare for interviews, track application outcomes, sync status with Gmail and Notion, and analyze skill gaps for future learning.

Who it’s for

Job seekers who are comfortable with a command-line interface and have a LaTeX distribution installed, specifically those looking to automate the tailoring of their professional documents without sacrificing quality or authenticity.

Highlights

  • PDF Verification Loop: Automatically iterates on LaTeX code until the PDF layout is visually clean and fits the page limits.
  • Drafter-Reviewer Pipeline: Uses two separate AI agents to draft and critique applications to improve quality.
  • ATS-Check: Verifies that the compiled PDF is actually parseable by Applicant Tracking Systems.
  • Comprehensive Lifecycle: Covers everything from initial scraping and fit-ranking to interview prep and skill-gap analysis.

Written about in

Related

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that provide multi-agent academic reviews for research papers, grant proposals, and pre-analysis plans, including paper-code reproducibility checks.

  • Project
    Rzna-5559/Mrite

    A one-stop repository for mathematical modeling competitions that integrates automated solving via Claude Code, LaTeX paper templates, and a library of common algorithms.

  • Project
    luwill/research-skills

    A collection of Claude Code skills designed to automate academic research workflows, including exhaustive literature retrieval, verified proposal writing, and high-fidelity slide generation.

  • Project
    Hainrixz/the-architect

    A Claude Code meta-agent that designs rigorous software blueprints with verified stacks and strict acceptance criteria to guide autonomous AI builders.