About this role
Join our team as a Senior Red Team AI Security Engineer to proactively test and enhance the security of our generative AI systems. You will simulate adversarial attacks, evaluate ethical risks, and develop custom tools to safeguard AI integrity. This role offers a unique opportunity to shape best practices in AI security and collaborate with leading researchers.
What we are looking for 6
- Lead red team operations targeting AI/ML systems
- Simulate adversarial attacks like prompt injection and data poisoning
- Evaluate AI systems for ethical risks and biases
- Develop custom tools and exploit frameworks for AI security
- Research emerging AI threats and offensive AI techniques
- Mentor junior engineers and collaborate with AI teams