All projects
Solo buildAugust 19, 20266 min readView live

JobTailor: AI Job Application Automation

A full-stack AI pipeline that scrapes 8+ remote job sources, tailors a LaTeX resume per job using LLMs, compiles PDFs, and opens applications for human-in-the-loop submit. Runs daily at 7am.

Portrait of Mueed Nazir Bhat

Mueed Nazir Bhat

AI Automation & Performance Marketing · Anarchy Labs

Short answer

JobTailor is an open-source tool I built to automate the most repetitive part of job hunting: finding roles, rewriting your resume for each one, and preparing the application. It runs every morning, finds 15+ remote jobs, and hands you a stack of tailored PDFs ready to submit.

PythonLLMsFastAPINext.jsScraplingLaTeX

The problem

Job hunting means trawling multiple job boards, reading each description, rewriting your resume to match, and repeating that for every application. Most people either send the same generic resume everywhere or spend hours tailoring by hand.

What it does

JobTailor is a pipeline with five stages. Each stage does one thing and hands the result to the next:

  • Find jobs: searches multiple job boards and company career pages. Everything is filtered to remote-only.
  • Read jobs: pulls the full job description and extracts the skills and requirements the employer wants.
  • Rewrite resume: an LLM adjusts a LaTeX resume to highlight matching skills. Each version lives on its own git branch. The original is never touched.
  • Make PDF: compiles the rewritten LaTeX into a ready-to-upload PDF.
  • Open applications: opens each job's application page with the tailored PDF pre-attached. You review and click Submit.

The guardrail

The AI never invents skills or experience. It only rephrases, reorders, and emphasises what is already on the resume. Nothing ships that you could not defend in an interview.

Tech stack

  • Python package with five pipeline stages
  • Scrapling for anti-bot job scraping
  • LLM API for resume tailoring (OpenAI-compatible)
  • Tectonic for LaTeX to PDF compilation
  • Next.js + FastAPI dashboard for monitoring runs
  • ego-browser for application auto-fill
  • macOS LaunchAgent for daily scheduling

Results

The pipeline runs daily and produces a stack of tailored applications every morning. What used to take hours of manual work now takes minutes of review. Each resume is customised to the specific job description, and the human reviews every application before it goes out.

The project is open source. Anyone can install it, point it at their own resume and job keywords, and run their own automated job search.

Need this built, not just read?

I automate marketing workflows and run performance campaigns at Anarchy Labs.

Start a project