we are seeking a Staff-level Senior AI Security Researcher to join AI Adversarial Robustness Research (A2RS), a multidisciplinary team focused on securing AI and GenAI models and systems.
Were looking for innovative team players who love new challenges, enjoy cracking tough problems, and thrive in cross-functional environments.
In this role, you will partner with data scientists and security researchers to define how secures AI applications.
Responsibilities:
Research AI and GenAI systems from a security perspective to understand when and how they are vulnerable to a variety of threats
Blue team: Explore innovative ways to enhance the security of AI systems
Red team: Analyze the attack surface of state-of-the-art AI technologies
Center of Excellence: Collect and synthesize research literature and open-source tools to build and maintain a robust knowledge base for adversarial robustness of AI systems
Distill and share AI security knowledge within and externally through seminars, blogs, papers, and conference talks
Requirements: MSc (with thesis) or PhD in Computer Science, Applied Mathematics, or a related field; equivalent research experience considered with a proven record
6+ years of industry experience in cybersecurity research, including 3+ years in threat research, and 3+ years in security innovation (may overlap)
Strong background in data science and prompt engineering experience in AI security or AI research
Significant experience in research and innovation, including rapid prototyping, publications, conference talks, or patents
Strong abstract-thinking and problem-solving skill
This position is open to all candidates.