Nada Amin

About

Nada Amin is an Assistant Professor of Computer Science at Harvard SEAS and Associate Faculty at the Kempner Institute, where she combines programming languages (PL) and artificial intelligence to build intelligent systems that are correct by construction. Before Harvard, she was a University Lecturer in Programming Languages at the University of Cambridge and a member of the Scala team at EPFL, where she completed her PhD. Earlier, she was a software engineer at Google and earned bachelor’s and master’s degrees from MIT. She recently co-founded Midspiral to bring verification to mainstream AI-assisted software development.

Research Focus

Amin’s research lies at the intersection of programming languages (PL) and artificial intelligence, with the goal of building intelligent systems that are correct by construction. One line of work combines large language models (LLMs) with program verifiers, enabling large-scale generation of verified programs for training models and for finding targeted solutions. A second line develops neuro-symbolic languages that give neural systems explicit algorithmic structure by compiling typed programs directly to neurons. Her longer-term goal is a formal PL theory of intelligence grounded in the semantics of reflective computation, treating the LLM-verifier interface as a tractable setting. She also applies these tools to mine biomedical knowledge graphs with the Hugh Kaul Precision Medicine Institute.