RBC seeks an experienced Lead AI Security Researcher to spearhead threat research in AI/ML security within the financial sector. This full time, individual contributor role focuses on identifying emerging threats and developing robust defense strategies.
In this essential role, you will assess vulnerabilities and threat vectors specific to AI, enhancing RBC's position in enterprise AI security. With over 5 years of experience required, you will work on hands-on testing, design assessment frameworks, and collaborate across various teams to implement scalable solutions for AI technologies.
Key Responsibilities:
• Monitor and assess emerging AI security threats
• Research attack vectors like prompt injection and model poisoning




• Conduct thorough assessments of AI technology risk
• Execute hands-on security testing and validation
• Create impactful technical reports for diverse audiences
Requirements:
• 5+ years in security research and vulnerability assessment
• 2+ years in AI/ML security-related research
• Strong coding skills in Python, Go, or Java
• Solid understanding of AI/ML systems
• Excellent communication and writing abilities
Elevate your career by leveraging your expertise to influence RBC's AI security landscape.
#J-18808-Ljbffr

📌 Lead AI Security Researcher at RBC (Vancouver)
🏢 RBC
📍 Vancouver