{"slug": "i-built-a-job-search-agent-that-scores-200-jobs-with-local-ai-zero-cloud-zero", "title": "I Built a Job Search Agent That Scores 200 Jobs With Local AI -- Zero Cloud, Zero Cost", "summary": "A developer built JobRadar, a CLI tool that searches 8 job sources concurrently and scores each listing against a user's profile using a local LLM (qwen3-1.7b) running on the user's machine, with no cloud APIs or data leaving the computer. The tool provides a score from 0 to 100, a rating, and a reasoning paragraph for each job, and includes a FastAPI dashboard with Kanban-style application tracking.", "body_md": "Job searching is tab hell.\n\nYou open LinkedIn, Indeed, RemoteOK, Glassdoor. You re-read the same listings. You copy-paste the same cover letter. You pay $30/month for tools that just aggregate feeds and call it \"AI-powered.\"\n\nI wanted something better. So I built JobRadar.\n\nJobRadar is a CLI tool that searches 8 job sources concurrently and scores every listing against your profile using a local LLM running on your machine.\n\n```\npython -m jobradar -q \"python developer\" -p profile.yaml\n```\n\nThat's it. Eight boards searched in parallel. Every job scored 0-100. Results saved to CSV. Total time: under a minute.\n\nEvery other job search tool I found uses cloud APIs for scoring -- OpenAI, Claude, whatever. Which means your resume, your search history, your career preferences all go to someone else's server. And you pay per token.\n\nJobRadar runs qwen3-1.7b (1.1 GB) on your CPU via Ollama. No API keys. No subscriptions. No data leaving your machine. The AI scores each job on four dimensions:\n\nEach job gets a score, a rating (Excellent/Good/Fair/Poor), and a reasoning paragraph explaining why.\n\nMost job search tools scrape 1-2 boards. JobRadar hits 8 simultaneously:\n\nThe Greenhouse and Ashby sources pull directly from company career page APIs. No scraping, no auth, no fragility.\n\nYou define a profile YAML:\n\n```\nname: Anirudh\ntitle: Backend Engineer\nskills:\n- Python\n- FastAPI\n- PostgreSQL\n- Docker\nexperience_years: 5\nsalary_min: 120000\nremote_ok: true\n```\n\nJobRadar sends each job description plus your profile to the local LLM and gets back structured JSON with scores and reasoning. The model runs on your CPU -- no GPU required. On my machine (15GB RAM, no GPU), it processes about 9 seconds per job.\n\n| Feature | JobRadar | Cloud-based tools |\n|---|---|---|\n| AI scoring | Local LLM (free) | OpenAI API ($$) |\n| Data privacy | Stays on your machine | Sent to cloud |\n| Job sources | 8 concurrent | 1-3 |\n| Web dashboard | Yes (Kanban) | Depends |\n| License | MIT | Varies |\n| Setup time | `bash setup.sh` |\nAccount + API key |\n\nBeyond the CLI, there's a FastAPI dashboard with a Kanban-style pipeline to track your applications. Filters, search, config editor -- all running locally on port 3000.\n\n```\ngit clone github.com/ANIRudH-lab-life/job-radar\ncd job-radar\nbash setup.sh # or setup.ps1 on Windows\n\n# Pick Ollama (recommended)\npython -m jobradar -q \"python developer\" -p profile.yaml\n```\n\nMIT licensed. No vendor lock-in. Your data stays yours.\n\nGitHub: github.com/ANIRudH-lab-life/job-radar\n\nIf you find it useful, a star would mean a lot. If you have ideas for improvement, open an issue -- I read every one.", "url": "https://wpnews.pro/news/i-built-a-job-search-agent-that-scores-200-jobs-with-local-ai-zero-cloud-zero", "canonical_source": "https://dev.to/anirudh_shivam/i-built-a-job-search-agent-that-scores-200-jobs-with-local-ai-zero-cloud-zero-cost-21lk", "published_at": "2026-07-27 02:36:02+00:00", "updated_at": "2026-07-27 03:30:31.681042+00:00", "lang": "en", "topics": ["artificial-intelligence", "developer-tools", "ai-agents", "ai-products"], "entities": ["JobRadar", "Anirudh", "Ollama", "qwen3-1.7b", "FastAPI", "LinkedIn", "Indeed", "RemoteOK"], "alternates": {"html": "https://wpnews.pro/news/i-built-a-job-search-agent-that-scores-200-jobs-with-local-ai-zero-cloud-zero", "markdown": "https://wpnews.pro/news/i-built-a-job-search-agent-that-scores-200-jobs-with-local-ai-zero-cloud-zero.md", "text": "https://wpnews.pro/news/i-built-a-job-search-agent-that-scores-200-jobs-with-local-ai-zero-cloud-zero.txt", "jsonld": "https://wpnews.pro/news/i-built-a-job-search-agent-that-scores-200-jobs-with-local-ai-zero-cloud-zero.jsonld"}}