Join our team as a Principal AI Security Engineer, specializing in adversarial testing for AI systems. Your expertise will drive vulnerability assessments and risk mitigation in production environments. You will lead red teaming against AI models, specifically focusing on breaking systems through prompt injection and model manipulation.

This role requires your fluency in Python to create effective testing tools and your comfort in presenting complex findings to executive teams. Deep understanding of control frameworks like ISO 27001 and SOC 2 will be essential for mapping vulnerabilities. Key Responsibilities:
Execute hands-on red team operations against AI systems
Analyze risks associated with prompt injections and model exploitations




Communicate significant findings to executive audiences
Develop customized testing solutions using Python
Produce structured documentation for compliance Requirements:
Direct experience in red teaming LLM or AI-driven settings
Robust knowledge of adversarial machine learning techniques
Familiarity with enterprise security governance standards
Ability to articulate technical risk effectively
Proficient in Python for testing purposes Join us in enhancing AI system security and addressing potential risks head-on.

📌 Ai Red Team Principal Security Role Calgary
🏢 C-Serv
📍 Calgary