Daniel Wood

Dan Wood is a Senior HPC Engineer specializing in high-performance computing infrastructure, systems architecture, and performance engineering for research computing.

Dan has been responsible for the deployment and integration of major HPC environments including Ookami, SeaWulf, and NVwulf, and is currently working on the upcoming AMA27 system. He uses Bright Computing (BCM) to provision and manage HPC environments, and creates, maintains, and updates the software images used to deploy compute nodes across these systems.

His work spans Linux systems, Slurm workload management, NVIDIA GPU computing, InfiniBand networking, high-performance storage, monitoring, automation, and performance analysis. He develops scheduling and resource-management policies, integrates new compute and accelerator platforms, maintains production operating-system images, and troubleshoots complex hardware and software issues.

Dan has worked with a range of architectures, including Fujitsu A64FX, Intel Sapphire Rapids with HBM, AmpereOne, and NVIDIA GPU platforms. His experience covers the full HPC infrastructure stack, from individual compute nodes, GPUs, networks, and storage systems to the deployment, integration, imaging, and operation of complete production research computing environments.