Senior ai engineer (red team, llm, adversarial attacks, prompt injection, guardrails, policy bypass)
CharlottesvilleCapital One
...LLMs, guardrails, prompt injection, policy bypass, and end-to-end AI system exploitation across both Internal Foundational and External models. It’s a rare chance to join a team at inception and do deep, impactful work in AI security.In this role, you will: Partner with a cross-functional team of engineers, research [...]
Category Engineering & Architecture
9 days ago in Experteer