AI Security Engineer - Adversarial Focus

Become a key player in AI security as an AI Security Engineer, specializing in adversarial machine learning strategies. Your expertise will fortify AI systems against potential vulnerabilities. This role requires a deep understanding of LLM-driven AI systems and an attacker’s mindset to effectively identify weak spots.

You'll perform simulations of attack vectors, develop automation tools, and work closely with engineering teams to implement remediation strategies based on your findings. Key Responsibilities: • Lead adversarial testing across various AI systems • Simulate real-world attack scenarios including data manipulation • Create tools to automate adversarial testing • Assess model responses to adversarial inputs • Clearly document research outcomes and vulnerabilities Requirements: • Proven experience in adversarial ML or AI security • Competence with LLM-based systems like Anthropic • Strong Python coding abilities • Knowledge of RAG architectures and fine-tuning • Cybersecurity background preferred Apply your innovative thinking to enhance the security of AI deployments at scale. #J-18808-Ljbffr