Principal Researcher in AI Security at RBC

Join RBC as a Principal Researcher in AI Security in Toronto, Canada, where you'll lead critical AI/ML threat assessments. This full-time role emphasizes defensive research on generative AI systems.

In this pivotal position, you’ll spearhead efforts to identify and mitigate risks within RBC’s AI platforms. Your focus will be on researching prompt injection and automated attack systems while collaborating with AI engineers to shape security strategies. The role requires deep technical insights and 7 years of industry experience to drive impactful change.

Key Responsibilities:

• Analyze emerging security threats specific to AI

• Conduct assessments on AI-driven social engineering risks

• Validate security controls through proof-of-concept testing

• Produce technical reports and analyses

• Work with external vendors to improve security products

Requirements:

• 7+ years in security and vulnerability research

• 3+ years researching AI/ML threats

• Profound coding skills in one or more languages

• Strong understanding of AI operational patterns

• History of influencing technical security strategies

Make a significant impact on AI security within RBC’s innovative environment.
#J-18808-Ljbffr