Career-Ops turns Claude Code into an AI job search pipeline. 12 modes, A-F scoring across 10 dimensions, ATS-optimized CVs per listing, batch processing of 122 URLs in parallel. 631 evaluations, 68 apps sent. Open source, 9.1K GitHub stars.
@santifer built a multi-agent job search system on Claude Code, ran 631 evaluations, sent 68 applications, and landed a Head of Applied AI role, then open-sourced it.
The problem: searching for senior AI roles is a full-time job. Read the JD, map your skills, rewrite the CV, fill 15-field forms, multiplied by 10 offers a day. 74% of offers are a poor fit. You find out after reading 800 words. The solution: Career-Ops automates the analysis. You make every final call.
What stands out:
🎯 A–F scoring across 10 dimensions with role match gate filters
📄 ATS PDFs per role with keywords, reordered bullets, auto region
🔍 Scanner across 45+ companies like Ashby, Lever, Wellfound
⚡ Batch mode runs 122 URLs in parallel with worker architecture
🧠 Story Bank builds reusable STAR+R interview answers
💰 Negotiation scripts for salary, geo gaps, competing offers
📊 Dashboard with filters, sorting, and lazy previews
🔁 680 URLs deduped with human review before submission
By the numbers:
631 evaluations, 516 unique offers
354 PDFs generated
68 applications sent
9.1K GitHub stars, 1.6K forks
Different because this isn't an auto-apply bot, it's a filter. The design principle is explicit: automate analysis, not decisions. And the system itself is the portfolio, building a multi-agent architecture to land multi-agent roles is the most direct proof of competence.
Perfect for senior engineers, AI practitioners, and anyone running a serious, high-signal job search at scale.
P.S. I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified →@rohanrecommends
Turning job search into a structured, almost pipeline-driven system is a very cool approach — especially with scoring and parallel processing, that’s a level of rigor most people don’t have.
We also launched on Product Hunt a few days ago, so can definitely relate — hope you’re having a great launch day. Wishing you strong traction!
real agent, not a chat wrapper - using Claude Code for file iteration is the right call. the drift question matters though: one bad filter config and it's applying to roles you excluded.
Rohan being Rohan! It's more than cool mate. Not only cause he solved a real pain but also cause he open-sourced it to make the life of others easier than ever
Hey everyone! I'm Santiago, the creator of career-ops.
I built this during my own job search. After months of sending applications into the void, I decided to automate the entire process with Claude Code. The system evaluated 740+ offers, I applied to 66, got 12 interviews, and landed a Head of Applied AI role.
The irony? The job I accepted actually came inbound, a CEO saw my systems thinking and liked my mindset. Turns out, building the tool was the ultimate proof of competence.
I open-sourced it because I believe the hiring system is broken. Companies use AI to filter candidates — candidates deserve the same tools to filter companies.
Happy to answer any questions about the architecture or how it works!
Congrats on the launch Santiago! Love the multi-agent approach for high-signal job searching.
I built precis.top, a lightweight resume builder that focuses on clean, ATS-friendly structures. Since Career-Ops excels at generating tailored content, it could be a perfect 'last mile' partner—Career-Ops handles the intelligence, and Precis handles the professional presentation.
@santifer built a multi-agent job search system on Claude Code, ran 631 evaluations, sent 68 applications, and landed a Head of Applied AI role, then open-sourced it.
The problem: searching for senior AI roles is a full-time job. Read the JD, map your skills, rewrite the CV, fill 15-field forms, multiplied by 10 offers a day. 74% of offers are a poor fit. You find out after reading 800 words. The solution: Career-Ops automates the analysis. You make every final call.
What stands out:
🎯 A–F scoring across 10 dimensions with role match gate filters
📄 ATS PDFs per role with keywords, reordered bullets, auto region
🔍 Scanner across 45+ companies like Ashby, Lever, Wellfound
⚡ Batch mode runs 122 URLs in parallel with worker architecture
🧠 Story Bank builds reusable STAR+R interview answers
💰 Negotiation scripts for salary, geo gaps, competing offers
📊 Dashboard with filters, sorting, and lazy previews
🔁 680 URLs deduped with human review before submission
By the numbers:
631 evaluations, 516 unique offers
354 PDFs generated
68 applications sent
9.1K GitHub stars, 1.6K forks
Different because this isn't an auto-apply bot, it's a filter. The design principle is explicit: automate analysis, not decisions. And the system itself is the portfolio, building a multi-agent architecture to land multi-agent roles is the most direct proof of competence.
Perfect for senior engineers, AI practitioners, and anyone running a serious, high-signal job search at scale.
P.S. I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified → @rohanrecommends