Summary
Shi Dong is a Senior Member of Technical Staff at Cerebras Systems with 10+ years bridging research and production in AI, high-performance computing, and big data analytics. He holds a Ph.D. in Computer Engineering and has driven GPU and accelerator-focused research from Northeastern to industry roles at AMD, Samsung, Intel, and MediaTek, including a pending patent for a low-overhead DNN sparsity monitor. At Cerebras he advances compute support for deep learning on novel hardware, combining systems-level optimization with practical deployment experience. Known on GitHub as a pragmatic implementer—"making things happen"—he balances academic rigor (Google Scholar profile) with hands-on engineering that improves scalability and memory efficiency in real workloads. A California-based engineer, he brings deep telecom and DSP roots to modern ML infrastructure problems, often surfacing non-obvious data patterns that inform architecture decisions.
10 years of coding experience