Summary
Sergey Zhumatiy is an HPC Cluster Architect and PhD in computer science with over two decades of hands-on experience designing, launching, and operating large-scale supercomputers, including seven MSU clusters of which five appeared on the TOP500. He combines deep academic credentials and prolific research output (78 articles, 3 books, 45 conference reports) with practical mastery of xCAT, Lustre, InfiniBand, SLURM and Linux systems administration since 1996. At NVIDIA and previously at SRCC MSU he’s been responsible for cluster governance, monitoring, alerting automation and user support, and he teaches and supervises students in supercomputer administration. Equally comfortable scripting in Ruby, Bash and Python as in low-level C/C++, Sergey is known for improving parallel program and system efficiency at scale. Based in Mountain View, he thrives on creative, team-based problem solving and has served on program committees for over 20 conferences.
15 years of coding experience
29 years of employment as a software developer
Московский Государственный Университет им. М.В. Ломоносова (МГУ)
Lomonosov Moscow State University
Английский, Russian