Principal AI Security Researcher (Global Security)

Job Description

Job Description What is the opportunity? This is an exciting opportunity to lead and shape the AI/ML threat research and security landscape for one of the world's biggest banks. The Principal AI Security Researcher (Global Security) will lead defensive threat research on generative AI and agentic AI systems. You will identify emerging threats, develop proof-of-concept exploits, and embed security into RBC's AI platforms as they're built—shaping our approach to AI security alongside our AI engineering teams. This is a technical, individual contributor role focused on making AI systems at RBC more secure by understanding how they could be attacked, validating mitigations, and advising engineering teams on the most critical threats to address first. What will you do? Monitor and analyze emerging AI security threats, vulnerabilities, and attack vectors specific to RBC's generative AI and agentic AI deployments Research attack vectors such as prompt injection, model manipulation, data poisoning, model theft, and AI supply-chain attacks Conduct threat landscape assessments tailored to RBC's AI technology stack and competitive position and assess risks from AI-driven social engineering, deepfakes, and automated attack systems Stay current with evolving AI security threats and defense mechanisms Develop proof-of-concept exploits that demonstrate security risks in RBC's AI systems Test and validate security controls and mitigations end-to-end (from POC through testing) Produce technical outputs including threat analyses, deep-dive reports, and whitepapers Work with AI security engineers and ML/AI/DevOps teams to prioritize threats and develop practical mitigations Collaborate with third-party AI security vendors to influence their roadmaps and product capabilities Test hypotheses about how emerging threats and defenses will impact RBC's systems and operations What do you need to succeed? Must-have 7 years of experience in security research and vulnerability research. 3 years of experience researching AI/ML security threats, attack vectors, or related domains. Strong coding experience in one or more general-purpose languages: Python, Go, Java, or similar. Expert understanding of AI/ML systems, architectures, and operational patterns. Proven ability to influence technical strategy and security decision-making Nice-to-have Published research, conference presentations, or open-source contributions in AI security Hands-on experience with large language models, multimodal models, and generative AI applications Experience with agentic AI systems Experience with security research labs, sandbox environments, or POC-to-production pipelines Experience collaborating with vendors and external security researchers What’s in it for you? We thrive on the challenge to be our best, progressive thinking to keep growing, and working together to deliver trusted advice to help our clients thrive and communities prosper. We care about each other, reaching our potential, making

Required Skills