AI Security Engineer - Adversarial Focus

Become an integral part of our AI Red Team as an AI Security Engineer focusing on adversarial methodologies. You will explore vulnerabilities within LLM systems and enhance AI resilience before enterprise rollout.
This critical role involves conducting comprehensive adversarial testing and simulating attacks against AI models. Your tasks will include prompt injection techniques, exploiting data pathways, and stress-testing AI deployments. You will work with engineering teams to document vulnerabilities and validate remediation strategies effectively.
Key Responsibilities:
• Conduct adversarial testing on LLM and AI systems
• Execute real-world attack scenarios and simulations
• Develop automation tooling for testing vulnerabilities
• Analyze model performance under adversarial conditions
• Collaborate for validation and remediation documentation
Requirements:
• Proven background in adversarial ML or AI security research
• Experience with LLM-based systems ...