Rate My Professor Riyadh Baghdadi

Riyadh Baghdadi is an Assistant Professor of Computer Science at New York University Abu Dhabi in the Division of Science, a Global Network Assistant Professor of Computer Science and Engineering at NYU Tandon School of Engineering, and a Research Affiliate at MIT's Computer Science and Artificial Intelligence Laboratory. He earned his PhD in Computer Science from Sorbonne University in 2015, affiliated with INRIA and École Normale Supérieure, advised by Albert Cohen; a Master's degree in Computer Science from Sorbonne University in 2011; and an Engineering Degree in Computer Science from École Supérieure d’Informatique in Algeria in 2010. From 2015 to 2020, Baghdadi served as a Postdoctoral Associate at MIT, where he led the development of Tiramisu, a polyhedral compiler for expressing fast and portable code in deep learning, tensor algebra, image processing, and scientific computing, presented at CGO 2019. During this time, he also collaborated on projects including GraphIt for graph analytics (OOPSLA 2018), Seq for computational biology (OOPSLA 2019), and optimizations for the Halide image processing compiler.

Baghdadi's research focuses on the intersection of applied machine learning and compilers, including machine learning-guided automatic code optimization, deep learning-based heuristics for compilers, and compilers optimized for machine learning hardware accelerators and resource-limited platforms such as smartphones and autonomous vehicles. His key contributions include a deep learning-based cost model for automatic code optimization, which earned the Outstanding Paper Award at the Fourth Conference on Machine Learning and Systems (MLSys 2021); Caviar, an e-graph-based transformation rewriting system for code optimization (CC 2022); and a deep learning model for loop interchange (CC 2023). Earlier work features PENCIL, a platform-neutral compute intermediate language for accelerator programming (PACT 2015). Baghdadi has received the Meta Research Award 2022 (AI4AI, $48,000), bronze medals at ACM Student Research Competitions (CGO 2015 and 2012), and Google Summer of Code 2010. He leads the Modern Compilers lab at NYUAD, has taught courses at NYUAD, MIT, and Sorbonne University, mentored 18 students, organized workshops such as the 12th International Workshop on Polyhedral Compilation Techniques (2022), and served on program committees for MLSys 2023, IPDPS 2023, PACT 2021, and editorial boards for ACM TACO, TOPC, and others.