End-to-end multi-tenant SaaS ATS built for SME recruitment agencies. Engineered with custom RAG retrieval pipelines, structured LLM prompt chains for resume parsing, and semantic candidate matching across active talent pools.
3,000+ candidates processed in 1.5 months
RAG & Few-Shot Prompts for 98% Parsing Precision
Sole Architect & Engineer from Schema to Infra
SME recruitment agencies waste hundreds of hours manually reviewing resumes, matching candidates, and managing pipelines. Traditional ATS tools rely on basic keyword matching that misses top-tier candidate nuance and contextual skills.
Designed & built multi-tenant SaaS backend with PostgreSQL schemas and Prisma ORM for total agency data isolation
Structured LLM prompt chains with JSON schema enforcement for zero-shot resume parsing and skill extraction
RAG (Retrieval-Augmented Generation) pipeline using dense vector embeddings for semantic candidate-to-job matching
Contextual candidate re-ranker evaluating candidate depth against job specs with automated reasoning summaries
Next.js full-stack agency dashboard featuring real-time candidate pipelines and automated applicant scoring
Containerized production deployment on DigitalOcean with automated database backups and zero-downtime migrations
Designed resilient prompt templates and few-shot examples to accurately parse noisy PDF/DOCX resume layouts into structured candidate JSON with 98% field precision
Built RAG semantic search over candidate vectors, balancing dense similarity scores with recruiter filtering constraints
Architected multi-tenant database isolation ensuring absolute data privacy and zero cross-agency leakages across active accounts