Summary
Min Kim is a Ph.D.-trained technologist with a decade of experience at the intersection of machine learning, digital hardware, and storage systems, currently advancing ML acceleration at Sandisk. He combines RTL-to-physical digital design expertise with software proficiency in C++, SystemC, Python and ML frameworks to deliver FPGA/NPU-accelerated inference and in-storage processing for SSDs. His background includes modeling and statistical error analysis of neural networks, production-focused toolflow experience (Synopsys, Vivado, PrimeTime) and hands-on work with Arm Ethos/U and Corstone IP. Min has driven projects from research prototypes—gem5-based SSD models and MNIST FPGA accelerators—to product planning for computational storage, demonstrating uncommon fluency across simulation, silicon-oriented verification, and ML workload optimization. Based in Irvine, CA, he pairs rigorous academic training with practical delivery and a knack for turning complex device-level constraints into deployable ML acceleration solutions.
10 years of coding experience
6 years of employment as a software developer
Bachelor’s Degree Engineering Science, Bachelor’s Degree Engineering Science at University of Toronto
University of California, Irvine
English, Korean