from Hacker News

Recently, I was exploring the OpenAI Agents SDK and building MCP agents and agentic Workflows.

To implement my learnings, I thought, why not solve a real, common problem?

So I built this multi-agent job search workflow that takes a LinkedIn profile as input and finds personalized job opportunities based on your experience, skills, and interests.

I used:

- OpenAI Agents SDK to orchestrate the multi-agent workflow - Bright Data MCP server for scraping LinkedIn profiles & YC jobs. - Nebius AI models for fast + cheap inference - Streamlit for UI

(The project isn't that complex - I kept it simple, but it's 100% worth it to understand how multi-agent workflows work with MCP servers)

Here's what it does:

- Analyzes your LinkedIn profile (experience, skills, career trajectory) - Scrapes YC job board for current openings - Matches jobs based on your specific background - Returns ranked opportunities with direct apply links

Here's a walkthrough of how I built it: https://www.youtube.com/watch?v=zNTWmw72BDs

The Code is public too: https://github.com/Arindam200/awesome-ai-apps/tree/main/adva...

Give it a try and let me know how the job matching works for your profile!