Lead Engineer/Engineer, Red Team, xCyber

Strengthen the security of AI models and systems by detecting, mitigating, and preventing adversarial attacks through proactive defence (Blue Team) and rigorous offensive testing (Red Team). Simulate and counter Adversarial AI Threats by conducting red/purple teaming to identify vulnerabilities, while implementing robust countermeasures to safeguard AI‑driven applications. Advance AI security research by developing AI security techniques, collaborating with cross‑functional teams, and contributing to the security frameworks that protect AI systems from evolving threats.

• Assess, develop and provide guidance on security measures to reinforce the security of AI models.
• Develop AI‑specific playbooks for responding to adversarial AI threats.
• Simulate red team attacks to uncover vulnerabilities in AI models.
• Generate adversarial examples to test and improve model robustness.