We are seeking to hire a Research Associate who will contribute to NTU’s mission of advancing cutting-edge research in large language model (LLM) safety, adversarial robustness, and secure AI agent systems.

Responsibilities:

• Conduct cutting-edge research in large language model (LLM) safety, adversarial robustness, and secure agent architectures.

• Design novel algorithms to defend against jailbreaking, backdoor implantation, and resource consumption attacks in LLMs.

• Develop evaluation benchmarks and frameworks for LLM alignment, safety, and interpretability.

• Collaborate with leading academic and industry partners to strengthen NTU’s role in global AI safety research.

• Prepare and publish high-impact research papers in premier venues (e.g., ICLR, ACL, EMNLP, ICML, AAAI).

• Support national and international research grant proposals in AI safety and trustworthy AI domains.

• Mentor postgraduate students and junior researchers in AI safety-related projects.

• Disseminate research findings through conferences, invited talks, and outreach activities

Requirements:

• Master’s degree in Computer Science, Artificial Intelligence, or a related discipline.

• Strong research track record with publications in top-tier conferences (e.g., ICLR, ACL, EMNLP, ICML, AAAI).

• Demonstrated expertise in LLM safety, adversarial robustness, jailbreak defenses, and model interpretability.

• Experience in designing large-scale evaluation benchmarks for AI alignment and safety.

• Background in security of AI agents, including backdoor detection, adversarial attacks, and defense methodologies.

• Proficiency in Python, deep learning frameworks (e.g., PyTorch, TensorFlow), and LLM fine-tuning techniques.

• Strong analytical and problem-solving skills in AI safety research.

• Excellent written and verbal communication skills for academic and professional dissemination.

We regret that only shortlisted candidates will be notified.

Hiring Institution: NTU