Reza Mokhtari
About Reza Mokhtari
Reza Mokhtari is a Principal Engineer at Cerebras Systems, with a strong background in system performance optimization and a deep understanding of processor micro-architecture. He previously held positions at NVIDIA and Untether AI, and earned his Ph.D. in Computer Engineering from the University of Toronto.
Work at Cerebras Systems
Reza Mokhtari has been serving as a Principal Engineer at Cerebras Systems since 2021. In this role, he focuses on system performance characterization and optimizations, leveraging his extensive experience in software architecture and chip development. His work involves leading initiatives that enhance the efficiency and effectiveness of AI processing systems.
Previous Experience at NVIDIA
Before joining Cerebras Systems, Reza Mokhtari worked at NVIDIA as a Senior Systems Software Engineer from 2016 to 2020 in the Toronto, Canada Area. He contributed to various projects related to system software, focusing on performance optimizations. Additionally, he held a brief position as a Systems Software Engineer at NVIDIA in San Jose for three months in 2015.
Education and Expertise
Reza Mokhtari earned his Doctor of Philosophy (Ph.D.) in Computer Engineering from the University of Toronto, where he studied from 2011 to 2016. He also holds a Bachelor of Science (B.Sc.) in Computer Science from Iran University of Science and Technology, completed between 2005 and 2009. His academic background provides a strong foundation for his expertise in processor and accelerator micro-architecture.
Background in System Software
Reza Mokhtari has extensive experience in system software, particularly in architecting compute drivers such as CUDA, which are essential for optimizing GPU performance. His background includes leading software bringup efforts and participating in the validation of AI processing chips, demonstrating a thorough understanding of chip development cycles.
Role at Untether AI
Prior to his current position, Reza Mokhtari worked at Untether AI as Team Lead and System Software Architect from 2020 to 2021. In this capacity, he was responsible for overseeing the development of system software and enhancing the interaction between users and hardware accelerators through high-level API design.