Position Summary The postdoctoral researcher will lead and contribute to research on next-generation AI systems, focusing on: Safety and alignment in generative AI and large language models (LLMs), multi-agent systems for reasoning, communication, cooperation, and decision-making, world models, machine unlearning, robustness, and adversarial machine learning, optimization foundations for safe and controllable AI. The candidate is expected to develop novel algorithms, publish in top-tier venues (e.g., NeurIPS, ICML, ICLR), and contribute to proposal writing and mentoring graduate students. Equal Employment Opportunity Statement All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gend