Ekdeep Singh Lubana

Ekdeep Singh Lubana is a member of technical staff at Goodfire AI, an interpretability startup focused on understanding and controlling AI systems. He previously served as a postdoctoral research fellow at Harvard University in the CBS-NTT Program on Physics of Intelligence and earned his PhD co-affiliated with the University of Michigan and Harvard's Center for Brain Science. He is known for research on AI alignment, interpretability, and the science of deep learning, including work on emergent capabilities, in-context learning, and scalable oversight protocols grounded in model internals.