HireRank - AI-Powered Hiring Platform

AI-powered resume ranking and shortlisting platform for early-stage startups.

Overview

HireRank helps startup founders and small teams efficiently process large volumes of resumes using AI-powered scoring and ranking. Instead of keyword matching, it uses semantic understanding to provide consistent, explainable candidate evaluations.

Key Features

• AI Scoring Engine: Weighted combination of semantic match, skill relevance, and experience alignment
• Structured Explanations: Clear strengths, gaps, and recommendations for each candidate
• Consistent Ranking: Same evaluation logic applied to all candidates
• Bulk Upload: Process up to 50 resumes per job posting
• CSV Export: Export shortlists for further processing

Tech Stack

Backend

• Python 3.11+
• FastAPI
• PostgreSQL
• SQLAlchemy + Alembic
• OpenAI (embeddings + completions)
• AWS S3 / MinIO (file storage)

Frontend

• React 18 + Vite
• TypeScript
• Tailwind CSS
• React Router

Project Structure

├── backend/                 # FastAPI backend
│   ├── app/
│   │   ├── api/            # REST endpoints
│   │   ├── core/           # Security, exceptions
│   │   ├── models/         # SQLAlchemy models
│   │   ├── schemas/        # Pydantic schemas
│   │   └── services/       # Business logic + AI
│   └── requirements.txt
│
├── frontend/               # React frontend
│   ├── src/
│   │   ├── api/           # API client
│   │   ├── components/    # UI components
│   │   ├── context/       # React context
│   │   └── pages/         # Page views
│   └── package.json
│
└── README.md

Quick Start

Prerequisites

• Python 3.11+
• Node.js 18+
• PostgreSQL 14+
• MinIO (for local development) or AWS S3

Backend Setup

cd backend

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Copy environment file
cp .env.example .env
# Edit .env with your configuration

# Run database (assuming PostgreSQL is running)
# Create database: createdb hirerank

# Start server
uvicorn app.main:app --reload

Frontend Setup

cd frontend

# Install dependencies
npm install

# Copy environment file
cp .env.example .env

# Start development server
npm run dev

MinIO Setup (Local S3)

# Using Docker
docker run -d \
  -p 9000:9000 \
  -p 9001:9001 \
  -e MINIO_ROOT_USER=minioadmin \
  -e MINIO_ROOT_PASSWORD=minioadmin \
  minio/minio server /data --console-address ":9001"

# Create bucket: hirerank-resumes via MinIO console at http://localhost:9001

Environment Variables

Backend (.env)

DATABASE_URL=postgresql://postgres:postgres@localhost:5432/hirerank
SECRET_KEY=your-secret-key
OPENAI_API_KEY=sk-...
AWS_ACCESS_KEY_ID=minioadmin
AWS_SECRET_ACCESS_KEY=minioadmin
AWS_S3_BUCKET=hirerank-resumes
AWS_S3_ENDPOINT_URL=http://localhost:9000

Frontend (.env)

VITE_API_URL=  # Leave empty for development proxy

API Endpoints

Method	Endpoint	Description
POST	/api/v1/auth/signup	Create account
POST	/api/v1/auth/login	Login
GET	/api/v1/auth/me	Get current user
GET	/api/v1/jobs	List jobs
POST	/api/v1/jobs	Create job
GET	/api/v1/jobs/{id}	Get job details
POST	/api/v1/jobs/{id}/candidates/upload	Upload resumes
GET	/api/v1/jobs/{id}/candidates	List ranked candidates
GET	/api/v1/jobs/{id}/candidates/{cid}	Get candidate details
GET	/api/v1/jobs/{id}/export	Export CSV

AI Scoring Algorithm

Overall Score = 40% × Semantic + 35% × Skills + 25% × Experience

• Semantic (40%): Cosine similarity between JD and resume embeddings
• Skills (35%): LLM-evaluated match of required vs. present skills
• Experience (25%): Years and domain relevance alignment

MVP Limitations

• Synchronous processing (30-50 resumes per upload max)
• Single user per company account
• No real-time notifications
• No resume parsing for structured data (text extraction only)

License

MIT