DEV Community· Sinky Priya·· 2 小時前AI 評分28
AI-Resume & Portfolio Tailor：開源 AI 智能體按職位描述改寫履歷並生成求職信
AI-Resume & Portfolio Tailor
AI 導讀
AI-Resume & Portfolio Tailor 是一款開源 AI 智能體，根據用戶的履歷和目標職位描述改寫履歷要點、突顯匹配技能，並生成求職信。它透過 Ollama 在本機執行 Llama 3 (8B)，以 LangChain 編排並採用 FastAPI 後端；作者表示，本地推理可避免敏感履歷資料外洩，亦消除 API 成本障礙。
正文
Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission 💸
What I Built
- The Project: AI-Resume & Portfolio Tailor
- What it does: An open-source AI agent that takes a user's master resume and a target job description, then automatically rewrites bullet points, highlights matching skills, and generates a tailored cover letter in seconds.
- Who would pay for it: Job seekers, career switchers, and freelance professionals tired of manually tailoring applications.
- The problem it solves: Eliminates hours of tedious copy-pasting and keyword optimization required to pass modern Applicant Tracking Systems (ATS).
Demo
- Live App: https://ai-resume-tailor-demo.example.com
- Video Walkthrough: Watch 2-min demo on YouTube
Code
-
GitHub Repository:
{% github username/ai-resume-tailor %}
How I Built It
- Open-Source AI / Models: Built using Llama 3 (8B) running locally via Ollama, orchestrated with LangChain, and hosted with a lightweight FastAPI backend.
-
Architecture & Tech Stack:
- Frontend: Next.js & Tailwind CSS for a clean, fast dashboard.
- Backend: Python / FastAPI handling document parsing (PDF/DOCX) and prompt execution.
- AI Layer: Local Llama 3 instance to ensure zero data leaks of sensitive user resume information.
Why Does Open Innovation Matter?
Using open-source weights (Llama 3) and local inference tools completely eliminated API cost barriers. For a bootstrapped side hustle targeting budget-conscious job seekers, relying on closed, per-token commercial APIs would have made a free tier or low-cost subscription model impossible to sustain. Plus, handling personal career data locally provides a massive privacy selling point that users trust.
My Agent Session
-
DevRelay Session:
{% agent_session 9a8b7c6d %}
My First User
- The User: A former colleague who is currently interviewing for Senior Frontend roles.
- Their Feedback: "It took me 30 seconds to generate a custom resume version for a Netflix role that usually takes me an hour. I used it for three applications and landed two recruiter screens!"
- Monetization Check: They expressed immediate willingness to pay a \$9 one-off fee or a \$5/month power-user subscription to access unlimited generations and custom template exports.
Prize Categories
- Best Open-Source AI Side Hustle
- Best Local Inference App
來源：DEV Community · dev.to