Adversarial Machine Learning Engineer - Red Teaming

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Adversarial Machine Learning Engineer - Red Teaming based in Canada. The Adversarial Machine Learning Engineer - Red Teaming will play a key role in identifying, analyzing, and mitigating security risks in advanced AI systems. This position focuses on adversarial testing, model robustness, and AI security research across foundation models, applications, agentic systems, and data pipelines. You will investigate complex vulnerabilities, transform edge-case findings into actionable security insights, and help strengthen AI safety practices. The role combines deep machine learning expertise with an attacker mindset to uncover weaknesses before they can be exploited. Working closely with AI security teams, you will influence remediation strategies and improve the resilience of next-generation AI technologies. This is an opportunity to contribute to cutting-edge AI security initiatives in a collaborative, remote-first environment.