About this role
Conduct research into adversarial AI and AI security to advance robustness, security and trustworthiness of AI models/systems, and develop AI/ML techniques and tools to detect, assess and secure AI systems against malicious and emergent attacks. Work with software engineers and stakeholders across the AI lifecycle from threat modelling and red teaming to delivering secured AI models/systems.
Skills for this role
Machine LearningDeep LearningComputer VisionPythonPython AI frameworksAdversarial AIAgentic AIAI securityAI assuranceCybersecurityThreat modellingRed teamingAI/ML research and development