Principal Researcher in AI Security (Alberta)

Join RBC as a Principal AI Security Researcher and lead initiatives to enhance AI security across generative and agentic AI platforms. Utilize your advanced knowledge to mitigate threats and secure systems effectively. In this influential role, you will lead defensive research efforts against evolving AI security threats. With extensive experience in security research, you'll analyze vulnerabilities, test security controls, and produce detailed reports. Your insights will directly influence RBC's AI deployment strategies and security posture. Key Responsibilities: • Analyze emerging threats specific to AI systems • Research attack vectors such as prompt injection and AI supply chain attacks • Conduct tailored threat assessments for AI technology • Develop and validate end-to-end security mitigations • Collaborate with vendors on AI security innovations Requirements: • 7+ years in security research and vulnerability assessment • 3+ years focused on AI/ML security vulnerabilities • Proficiency in Python, Go, or Java coding • Deep understanding of AI/ML architectures • Demonstrated ability to guide security strategies Drive impactful research and security advancements for RBC's AI operations. #J-18808-Ljbffr Apply on Kit Job: kitjob.ca/job/2ooc5p