LLM Automation

AI-Powered CV Screening & Ranking

An n8n automation pipeline that pulls CVs from Google Drive, OCRs scanned PDFs with Gemini 2.0 Flash, scores candidates with GPT-4o against weighted job criteria, and ranks them into Google Sheets, cutting manual screening time by ~90%.

n8nGPT-4oGemini 2.0Workflow Automation

n8n.cloud/workflow/cv-screening

n8n automation workflow for AI-powered CV screening: triggers, CV ingestion from LinkedIn and websites, PDF download, OCR fallback via Gemini, GPT-4o scoring, and ranked output to Google Sheets

End-to-end n8n workflow 20+ nodes · dual triggers · OCR & error-handling branches

RoleAI Engineer, pipeline design

DomainLLM workflow automation

Overview

Built on n8n, the workflow runs on a manual or scheduled trigger, gathers CVs from both LinkedIn and website sources, tags and merges them, then filters out anything already processed so no candidate is scored twice. Each new PDF is downloaded and read, with a Gemini 2.0 Flash OCR fallback for scanned or image-based files. GPT-4o then scores every candidate against weighted, job-specific criteria, and the ranked result is written back to Google Sheets, with a dedicated error-handling branch logging any failures.

Key features

Dual triggers: run on demand or on an automatic schedule.
Multi-source ingestion from LinkedIn and website CV listings.
Automatic de-duplication against already-processed candidates.
OCR fallback for scanned / image-based PDFs via Gemini 2.0 Flash.
Weighted scoring against configurable role criteria with GPT-4o.
Ranked output in Google Sheets: ~90% less manual screening time.
Built-in error logging so failed items never break the run.