Summary
Jing-jing Li is a UC Berkeley PhD candidate blending cognitive neuroscience and computer science to advance AI safety, interpretability, and human-aligned ML. She has three years of research experience spanning academia and industry, including internships and fellowships at AI2, AWS, and Anthropic where she led projects on LLM safety, evaluation, tool use, and synthetic data. Her work draws on prior neuroimaging and electrophysiology expertise—developing ML classifiers for seizure impact prediction and decoding visual representations from fMRI—which informs her approach to model transparency and robustness. Jing-jing is actively seeking a Research Scientist role starting May 2026 and brings a rare combination of experimental neuroscience rigor and practical alignment engineering. Colleagues describe her research as both methodical and application-minded, often translating cognitive principles of learning and decision-making into safer ML interventions.
3 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD Computational Cognitive Neuroscience, Doctor of Philosophy - PhD Computational Cognitive Neuroscience at University of California, Berkeley
High School, High School at The High School Affiliated to Renmin University of China
Bachelor's degree Computer Science and Mathematics, Bachelor's degree Computer Science and Mathematics at Cornell University
Neuroscience, Neuroscience at William & Mary