InternshipWhat a AI Red Teaming intern does
The AI Red Teaming role, what you build at each level and what you need before you start.
Test AI systems the way attackers would, ethically and in your own lab: prompt injection, jailbreak categories, data leakage, bias, guardrails and professional reports.
What you build, level by level
- Level 1: Foundations: What AI red teaming is, How LLMs work, Threat landscape and more.
- Level 2: Building real features: Indirect prompt injection, Defences against injection, Tool and agent abuse and more.
- Level 3: Professional work and capstone: Multi-turn attack testing, Model supply chain, Adversarial examples and more.
Where this work is used
Training Trains, W3AppDevelopers and DomainHostly use these skills in real projects: Cyber Security, AI / Machine Learning Solutions. Interns who pass the readiness check can take paid-company work from the Company Work board in the portal.
Before you start
Python basics and an interest in security. All testing is on your own lab apps or with written permission.