Join a dedicated AI Red Team as an Adversarial Machine Learning Specialist. This hands-on role emphasizes identifying vulnerabilities in LLM-driven systems to enhance AI security before deployment.
In this technical position, your focus will be on conducting adversarial testing and executing real-world attack simulations. You will explore prompt injection, jailbreaking techniques, and data exfiltration attempts, while developing scripts to automate attack scenarios. Collaborating closely with engineering teams, you'll document findings and improve model guardrails for enterprise deployment.
Key Responsibilities:
• Conduct adversarial testing across AI-based systems
• Execute attack simulations like prompt injection and jailbreaking
• Develop automation scripts for attack scenarios
• Analyze model behaviors under stress conditions
• Collaborate with teams to validate remediation efforts
Requirements:
• Strong experience in adversarial ML or AI security
• De...