AI Resume Screening Platform Documentation

Overview

Production-ready AI-powered recruitment SaaS platform with multi-tenant architecture, bias detection, resume parsing, and candidate matching. Built with Django 5.2+, 15,000+ lines of code.

Demo Mode vs Full Version

The live demo at ai.djangozen.com/resume-screening/ runs in Demo Mode without API keys configured. In demo mode, candidate-job matching uses the built-in keyword-based engine rather than GPT-4. Match results in the demo display a notice indicating demo mode is active.

After purchasing the full version:

1. Add your OpenAI API key () to the file
2. Configure Redis and start Celery workers for background processing
3. Switch the matching engine to OpenAI Matching in Organization Settings > Scoring Settings for full AI-powered semantic matching

Where to get your API key:
- OpenAI: platform.openai.com - Create an account and generate an API key under API Keys

Quick Start

Requirements

• Python 3.10+
• PostgreSQL (recommended) or SQLite
• Redis (for Celery background tasks)
• OpenAI API key (optional, for AI matching)

Installation

# Clone and setup
git clone <your-repo>
cd ai-resume-screening-platform
python -m venv venv
source venv/bin/activate  # Linux/Mac

# Install dependencies
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env with your settings

# Run migrations
python manage.py migrate

# Create demo data (optional)
python create_demo_data.py

# Start development server
python manage.py runserver

Docker Setup

docker-compose up -d

Core Features

1. Smart Resume Parsing

Upload resumes in PDF, DOCX, DOC, TXT, or RTF format. The AI engine automatically extracts:
- Skills and competencies
- Work experience and duration
- Education and certifications
- Contact information

Batch Upload: Upload up to 50 resumes at once with drag-and-drop support.

2. AI Matching Engine

Two matching modes available:
- Keyword Matching (<1ms): Fast pattern-based matching using extracted skills
- OpenAI Matching (~500ms): Deep semantic matching using GPT-4o-mini

Configure matching in Organization Settings > Scoring Settings.

3. Candidate Ranking

Candidates are automatically scored and ranked by job fit. View:
- Overall match score (0-100%)
- Skill breakdown with individual scores
- Experience relevance rating
- Side-by-side comparison (up to 5 candidates)

4. Bias Detection & Fairness

Built-in bias detection for:
- Age bias: Detects age-related language in job descriptions
- Gender bias: Identifies gendered terms and suggests neutral alternatives
- Language bias: Flags cultural or language-specific requirements

Anonymous Screening: Remove identifying information (name, photo, age) for unbiased evaluation.

Fairness Reporting: Generate compliance reports tracking hiring metrics by demographics.

5. Multi-Tenant Architecture

Complete data isolation per organization:
- Each organization has its own jobs, candidates, and settings
- Role-based access: Admin, Recruiter, Hiring Manager, Viewer
- Team management with email invitations

6. Subscription Billing

Stripe integration with tiered plans:
- Configure plans in Django Admin > Payments
- Webhook handling for subscription events
- Usage-based billing support

API Documentation

Full REST API with JWT authentication:

POST /api/v1/auth/token/          # Get JWT token
GET  /api/v1/jobs/                # List jobs
POST /api/v1/jobs/                # Create job
GET  /api/v1/candidates/          # List candidates
POST /api/v1/resumes/upload/      # Upload resume
GET  /api/v1/matching/results/    # Get matching results
GET  /api/v1/analytics/dashboard/ # Dashboard stats

Configuration

Environment Variables

Celery Background Tasks

# Start Celery worker
celery -A config worker -l info

# Start Celery Beat (scheduled tasks)
celery -A config beat -l info

Live Preview

Visit ai.djangozen.com/resume-screening/ to see screenshots and feature overview.

Support

• Store: djangozen.com/ai-apps/app/ai-resume-screening-platform/
• Contact: djangozen.com/contact/