Shape AI security at the University of Toronto as an AI Security Architect and Red Team Lead. Drive adversarial testing capabilities and be the key authority on AI security threats.
This unique role allows you to operate independently in establishing and leading the university’s adversarial testing function for AI systems. With a focus on both strategy definition and effective communication with senior leadership, you will play a vital role in shaping responsible AI practices. Your expertise in AI security will help identify vulnerabilities, evaluate third-party vendors, and support the development of robust AI security frameworks.
Key Responsibilities:
• Develop the university's AI red teaming function from scratch
• Assess the AI threat landscape and define strategic needs
• Communicate explicit,



actionable recommendations to leadership
• Manage relationships with third-party red teaming providers
• Establish internal security checks for responsible AI deployment
Requirements:
• Bachelor’s degree in Computer Science, Cybersecurity, or related field
• Minimum of 5 years of cybersecurity experience
• At least 3 years focused on AI/ML security and red teaming
• Relevant certifications preferred (OSCP, CEH, etc.)
• Strong understanding of LLM architectures and AI attack vectors
Lead the future of AI security and contribute to a responsible deployment strategy at the University of Toronto.
#J-18808-Ljbffr

📌 AI Security Architect at University of Toronto
🏢 University of Toronto
📍 Toronto