We are seeking highly motivated and talented individuals, including PhD candidates (who aspire to pursue a doctoral degree) and Postdoctoral Researchers, to join our research team, with a focus on AI Security. This position offers a unique opportunity to work at the forefront of AI security research. The laboratory is in the active stage of establishment, so early participants will enjoy potential for professional advancement and leadership development in the long term. 

Number of Positions: 1-2 Position 

Duration: 2–3 years 

Supervisor: Professor Kun Yang: https://cnic.cas.cn/rcdw/yjy/202603/t20260311_8155339.html, whose research interests primarily lie in Cyberspace Security and AI Security. 

1. Conduct cutting-edge research on AI security theories and technologies, with a focus on large language models (LLMs), agents, and distributed learning paradigms. Key research areas include LLM security, Agent security, and federated learning security. 

2. Undertake research on graph and temporal graph representation learning, with an emphasis on graph anomaly detection under dynamic topologies. The goal is to improve the accuracy and robustness of detection methods in complex real-world scenarios. 

3. Explore multi-agent security issues, aiming to enhance the security and robustness of multi-agent collaboration through the study of cooperative decision-making mechanisms, adversarial defense strategies, and system fault tolerance. 

4. Publish high-impact academic papers in top journals and conferences related to AI security, and participate in relevant academic exchanges and research collaborations. 

1. Hold a PhD degree (for Postdoctoral Position only) in Computer Science, Electrical Engineering, Statistics, Data Science, Mathematics, or a closely related field. Candidates who have recently obtained their PhD or are about to defend their dissertation are also welcome (for Postdoctoral Position only). 

2. Possess solid proficiency in core AI theories and technologies, including deep learning, Transformer architecture, reinforcement learning, and Agentic AI. 

3. Have a strong theoretical foundation in AI security, coupled with excellent abilities in algorithm design, implementation, and engineering practice. Experience with programming languages (e.g., Python, TensorFlow/PyTorch) is required. 

4. Demonstrate a strong research track record (e.g., publications in top-tier academic journals/conferences) or clear research potential in AI security. 

Remuneration & Benefits 

We offer a competitive annual salary of 300,000–350,000 RMB (for Postdoctoral Position only), commensurate with the candidate’s qualifications and research experience. 

Application Instructions Interested candidates are invited to submit the following application materials via email: 

- Preference for candidates from US News Top 50 National Universities. 

- Curriculum Vitae (CV) including educational background, research experience, publications, and other relevant achievements. 

- Research Statement outlining your past research work, current research interests, and future research plans related to AI security. 

- Contact information of three professional references (including their names, affiliations, and email addresses). 

Please send all materials to either of the following email addresses: kun88.yang@gmail.com or yangkun@cnic.cn 

Review of applications will begin immediately and continue until the position is filled. We encourage early applications.