FindJobs-Agent
LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with a
What is FindJobs-Agent?
LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with adaptive difficulty.
Overview of FindJobs-Agent
What it is
FindJobs-Agent is a full-stack job search assistant that crawls job postings from major tech companies, analyzes them with LLMs, parses resumes, and runs AI mock interviews. It is designed to help users focus on preparing rather than sifting through job boards. The entire loop can run in one terminal session offline, with 54 sample postings crawled and structured, resume-job skill gaps, and a mock interview with a feedback report.
Key features
- Job crawler that pulls postings from Tencent, NetEase, ByteDance, Amazon and more via API or Selenium, with automatic cleaning and normalization.
- LLM analysis that extracts education/major requirements, scores skill tags (1–5), and classifies each posting into a job taxonomy.
- Resume parsing and matching that parses PDF/Word resumes, scores skills, and computes a case-insensitive job-resume match percentage.
- AI mock interview that generates questions from any job description and runs a multi-turn interview with real-time feedback.
- Demo mode: set FINDJOBS_DEMO=1 to run the full app offline with seeded sample jobs, a bundled sample resume, and a deterministic stub LLM instead of a paid key.
- SQLite persistence: analyzed postings, uploaded resumes, and mock-interview transcripts are stored in a local jobs.db.
- Incremental crawls: a seen-ledger in jobs.db skips already-fetched postings to save LLM budget.
Use cases
- Job seekers who want to automatically collect and analyze job postings from multiple companies.
- Candidates who need to compare their resume against job requirements and identify skill gaps.
- Individuals preparing for interviews who want to practice with AI-generated questions tailored to specific job descriptions.
- Recruiters or career coaches who want to structure job data and simulate interview processes.
Getting started
Prerequisites: Python 3.10+, Node.js 18+, Chrome (for Selenium crawler). Clone the repo: bash git clone https://github.com/he-yufeng/FindJobs-Agent.git cd FindJobs-Agent Install the backend: bash pip install findjobs-agent # from PyPI # or for development: pip install -e . Set up your API key: create an API_key.md file with your OpenAI API key. Start the backend: bash python -m findjobs.api_server Start the frontend: bash cd FrontEnd npm install npm run dev Open http://localhost:5173 in your browser.
License and pricing
The project is licensed under the MIT license and is open source.
Based on the project's public README and repository metadata.