Built an end-to-end recruitment platform automating candidate screening with AI

Hirenex is an end-to-end recruitment platform that automates the most expensive part of hiring: the early-funnel screening. Instead of recruiters manually reviewing every resume, the platform uses AI-powered analysis to filter candidates against job-specific criteria, surfacing the best matches first.

The goal isn't to remove humans from hiring — it's to remove the busywork, so recruiters spend their time on conversations, not skimming PDFs.

Resume screening is inherently async and bursty — a single job posting can pull in hundreds of applications at once — so the platform had to queue and process resumes reliably in the background rather than blocking on every upload.

I architected and developed the complete resume-screening flow as a full-stack solution — integrating AI-powered resume analysis with NLP to automate candidate filtering based on each job's specific criteria.

The stack combines Django + Celery for async processing, PostgreSQL + Redis for persistence and queues, Qdrant for semantic candidate matching, and React + Next.js on the frontend. Document parsing runs through Docling, with Vanna.AI, Ollama, and the OpenAI API handling the language understanding side.

I owned the pipeline from resume upload through parsing, embedding, criteria matching, and final ranking — containerizing the whole stack with Docker so it deploys consistently across environments, with WebSockets pushing screening status updates back to recruiters in real time.