Built an end-to-end automation pipeline

Built an end-to-end automation pipeline to extract and structure data from 30,000+ resumes across multiple file formats including PDF, HTML, PNG, JPG, and DOCX.

Used n8n parsing modules for standard files and integrated LlamaIndex for resumes that could not be parsed directly. Applied an OpenAI node to identify and structure key candidate details — first name, last name, phone, email, state, and years of experience — and automated the migration of enriched data into Monday boards for seamless tracking and management.