AI Red Teamer

EY GDS — India

### Summary - Hiring AI red teamers to perform adversarial testing of LLMs and agentic workflows as part of an AI governance practice. ### Responsibilities - Adversarial testing across LLMs and multi-step agentic/tool-use exploits. - Build repeatable red teaming frameworks aligned with OWASP and MITRE guidance. - Collaborate with governance, risk, and delivery teams to translate findings into controls. ### Requirements - Hands-on experience red teaming LLMs or AI agents. - Background in security and guardrails; ability to work at intersection of technical exploit-finding and enterprise risk.