Microjobs Portal
A local part-time job board with an AI-powered recommendation system using TF-IDF and FAISS for fast similarity search.
Overview
A full-stack job portal targeting local micro and part-time jobs, with an intelligent recommendation engine that matches users with relevant job listings based on their skills and interaction history.
Problem Statement
Existing job platforms are optimized for full-time, large-company listings. Local micro-job seekers struggle to find relevant opportunities efficiently. A tailored portal with smart recommendations can dramatically improve match quality and time-to-hire.
Architecture
- Frontend: Next.js with Tailwind CSS and Shadcn UI components
- TF-IDF vectorization for job description representation
- FAISS index for approximate nearest-neighbor similarity search
- Recommendation engine combining content-based and interaction-based signals
Challenges
- ✗Cold start problem for new users with no interaction history
- ✗Efficiently searching across a growing job listing database
- ✗Balancing relevance vs. recency in recommendations
Solutions
- ✓Content-based fallback using TF-IDF cosine similarity for cold-start users
- ✓FAISS for sub-millisecond similarity search at scale
- ✓Configurable sort: relevance score or geographic proximity
Lessons Learned
- 💡FAISS dramatically outperforms brute-force cosine similarity at scale
- 💡Shadcn UI accelerates building accessible, polished components
- 💡Good data preprocessing is 80% of recommendation quality
Related Projects
Brain CT Scan Classifier
Multi-label classification system for brain CT scans using ConvNeXt-V2 and Multiple Instance Learning with a dual-head architecture.
AI Customer Support Chatbot
RAG-based chatbot that resolves customer complaints by retrieving similar past cases and generating responses with a local LLM.
Snake Maramari — Multi-Snake AI Battle
A competitive snake game in Python and Pygame where up to 4 AI snakes with different algorithms fight for survival and steal scores.