School of Electrical and Electronic Engineering is one of the founding Schools of the Nanyang Technological University. Built on a culture of excellence, the School is renowned for its high academic standards and research. With over 3,000 undergraduates students and 2,000 graduate students it is one of the largest EEE schools in the world and ranks 4th in the field of Electrical & Electronic Engineering in the 2025 QS World University Rankings by Subjects. For more details, please view: https://www.ntu.edu.sg/eee
We are looking for a Research Fellow to advance cutting-edge research in the security, robustness, and trustworthiness of multimodal AI agents. The role will focus on identifying novel attack vectors, developing automated red-teaming frameworks, and designing defense mechanisms to ensure the safe deployment of autonomous agents that integrate vision, language, and action.
Key Responsibilities:
Design and execute high-impact research on the security vulnerabilities of multimodal Large Language Models (MLLMs) and their agentic implementations.
Develop and benchmark novel adversarial attacks and defense strategies, focusing on the intersection of computer vision, natural language processing, and system-level tool execution.
Publish original research findings in top-tier AI and Security conferences.
Collaborate with interdisciplinary teams to translate theoretical security frameworks into practical safety guardrails for real-world agentic deployments.
Assist in the mentorship of PhD and Master students and contribute to the preparation of research grant proposals and technical reports for the university and funding agencies.
Job Requirements:
PhD qualification degree in Computer, Electrical or Electronic Engineering or related field
At least 3 years of relevant research experience in AI security related topics
Familiarity with multimodal architectures, agentic frameworks, and common security vulnerabilities in LLMs
Good written and oral communication skills in presenting complex technical findings to diverse academic and industrial audiences.
Proficiency in Python and deep learning frameworks such as PyTorch. Experience with Linux environments and GPU cluster management is essential.
Competent in analytical thinking and experimental design, specifically in evaluating model robustness against adversarial threats
Interpersonal skill: Ability to work independently and drive a research agenda while being a collaborative team player. Exhibit strong time management skills, and be able to meet strict project milestones.
Entry level candidates are welcome to apply
We regret to inform you that only shortlisted candidates will be notified.
Hiring Institution: NTU