How do you test AI agents for security vulnerabilities like prompt injection?
What tools, techniques, and benchmarks do you use to red-team your agents?
Hiring in Paris 🇫🇷 for my Applied AI team at
@OpenAI
It's Codex focussed, combining work with frontier startups, engaging the ecosystem, & getting feedback to product/research
Plus you'll work alongside my team of MLEs, ex-founder/CTOs, research engineers. Apply below ⬇️