Take the lead as a Senior AI Security Consultant in our AI Red Team, focused on hands-on adversarial testing. This role tackles security vulnerabilities in production AI systems urgently.
You will spearhead red team efforts, using your knowledge of adversarial machine learning to uncover weaknesses in real-world applications. Your fluency in Python should help you construct testing tools, while your ability to engage with executive teams will facilitate transparent communication about risk mitigation. Experience with ISO 27001 and SOC 2 will be critical to ensure compliance.
Key Responsibilities:
• Lead impactful red team engagements against AI systems
• Identify vulnerabilities via thorough adversarial testing
• Translate testing outcomes into executive-friendly recommendations




• Create and modify testing tools efficiently using Python
• Generate explicit, audit-ready documentation to support risk assessments
Requirements:
• Proven track record in red teaming LLM or AI systems
• In-depth knowledge of AI architectures like RAG and vector DBs
• Familiarity with ISO 27001 and SOC 2 governance frameworks
• Excellent communication skills for conveying technical issues
• Solid Python programming skills for tool development
Enhance your career by addressing security challenges in AI with our dedicated red team.
J-18808-Ljbffr

📌 Senior Ai Security Consultant Red Team Calgary (Canada)
🏢 C-Serv
📍 Canada