Strengthen AI defenses as an Adversarial Machine Learning Engineer. This impactful role focuses on identifying and exploiting vulnerabilities in LLM-driven systems.
We are building a dedicated AI Red Team to rigorously test our enterprise-scale AI products. You will be at the forefront of this initiative, conducting adversarial testing and stress-testing AI deployments to ensure they are secure and resilient. Your technical expertise will be integral to documenting findings and collaborating with engineers for remediation.
Key Responsibilities:
• Execute adversarial testing on AI and LLM systems
• Perform prompt injections and model jailbreak simulations
• Develop automation scripts for attack defense scenarios
• Analyze system behavior under attack conditions
• Collaborate with engineering teams for effective fixes
Requirements:
• Extensive experience in adversarial ML or AI security
• Strong background with LLM-based systems
• Proficient in prompt inj...