AI Security Researcher; Global Security

Job Description What is the opportunity?

RBC is seeking a Staff AI Security Researcher (Global Security) to lead threat research and vulnerability assessment in AI/ML security, a critical and rapidly evolving domain for financial services. This individual‑contributor role will identify emerging AI‑specific threats, develop and validate defense mechanisms, and help establish RBC's position as a trusted voice in enterprise AI security. You will work across business units, security teams, and third‑party vendors to translate cutting‑edge research into practical, scalable mitigations for RBC's AI technology stack.

• Monitor, analyze, and assess emerging AI security threats, vulnerabilities, and attack vectors relevant to RBC's environment and the broader financial services sector
• Research AI‑specific attack vectors including prompt injection, jail breaking, model poisoning, data poisoning, model theft, supply‑chain attacks, and adversarial evasion techniques
• Assess risks from AI‑enabled threats such as social engineering, synthetic media (deepfakes), and automated attack systems targeting RBC's infrastructure, data, and customers
• Conduct threat landscape assessments specific to RBC's AI technology stack, competitive position, and risk appetite

• Execute hands‑on testing of critical AI applications, including prompt injection, jail breaking, and adversarial attack simulations to validate security posture
• Design and implement consistent, scalable assessment frameworks and methodologies to standardize AI security evaluations across RBC's critical applications
• Develop proof‑of‑concept exploits and validation controls to demonstrate attack feasibility and test mitigation effectiveness
• Collaborate with AI/ML/Dev Ops teams, AI security engineers, and third‑party vendors to design practical defense strategies and controls

• Produce high‑impact technical outputs including deep‑dive threat analyses, research reports, and whitepapers for internal and external audiences
• Partner with third‑party AI security technology providers to influence product roadmaps and industry standards
• Stay current with evolving AI security threats, defensive capabilities, and industry best practices
• Contribute to RBC's AI Security research strategy and roadmap

Must‑have:

• 5+ years of experience in security research and vulnerability research.
• 2+ 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.
• Understanding of AI/ML systems, architectures, and operational patterns.
• Excellent organizational, communication, interpersonal, and technical writing skills.
• Proven ability to influence technical strategy and security decision‑making.

Preferred:

• Published research, conference presentations, or open‑source contributions in AI security.
• Experience with large language models and generative AI applications.
• Experience collaborating with vendors and external security researchers.

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 a difference to our communities, and achieving success that is mutual.

• A comprehensive Total Rewards Program including bonuses and flexible benefits
• Leaders who support your development through coaching and managing opportunities
• Ability to make a difference and lasting impact
• Work in a dynamic, collaborative, progressive, and high‑performing team
• Access to a variety of job opportunities across business and geographies