Justin Miller

Senior Systems Integration Engineer (Apr 2019 – Present)

(Incorporates duties previously held as Senior System Test Engineer from Apr 2019 - Mar 2020)

• Testing Framework & Automation
  • Develop and maintain Python-based integration testing framework, enabling end-to-end system validation from bare metal to application layer.
  • Utilize and add to Cray’s extensive database of test cases to test system-level functionality.
  • Develop automation workflows and comprehensive test suites to validate functionality and identify performance regressions.
  • Execute large-scale stress and endurance testing to identify potential failure points before deployment.
  • Validate GPU-accelerated workloads across NVIDIA and AMD environments, ensuring optimal performance.
• HPC System Management & Software
  • Test and validate both Cray System Management (CSM) software and HPE Performance Cluster Manager (HPCM) for HPC/AI clusters.
  • Install and administer Shasta (now CSM), Cray/HPE’s Kubernetes-based platform that enables converged HPC/ML/AI workflows.
  • Work with Slurm and PBS workload managers to validate job scheduling and resource allocation.
  • Validate and test Singularity container workflows using Slurm in the HPE Cray EX runtime environment.
• Programming Environment & Applications
  • Test and validate the HPE Cray Programming Environment (CPE) across multiple architectures including ARM, x86-64 (Intel/AMD), and GPU accelerators (NVIDIA/AMD).
  • Build, deploy, and validate diverse HPC/AI applications and benchmarks with focus on performance and scalability.
• Networking & Interconnects
  • Develop and execute tests for HPE Slingshot that verify health and configuration of the high-speed network fabric.
  • Test and validate both Slingshot 10 (Mellanox ConnectX HCA with HPE switches) and Slingshot 11 (HPE Cassini NIC with HPE switches).
  • Work with libfabric across multiple providers including Mellanox and HPE.
• Collaboration & Customer Focus
  • Apply unique end-user perspective to ensure solutions meet customer requirements for reliability, usability, scale, and performance.
  • Collaborate closely with Support teams to triage, root cause, analyze defects, and capture reproducers for complex customer issues.
  • Work with sales support and benchmarking engineers to run reproductions of customer workflows and develop tests for specific metrics.
  • Provide technical, experiential, and architectural feedback to product owners and R&D teams.

Storage Quality Engineer (Jan 2015 – Mar 2019)

• Worked alongside development teams to create and execute tests used to verify functionality of the Lustre client and server for the Cray Linux Environment and ClusterStor storage appliance.
• Designed and executed tests verifying features and functionality of Linux kernel module based Lustre client and server (ext4 and ZFS backing storage).
• Demonstrated advanced skills in the configuration, administration of Lustre using ext4 and ZFS as backing filesystems and LNet networking.
• Architected, deployed, and operated CI pipeline for Lustre using Jenkins and OpenStack.
• Analyzed failure patterns and improved test coverage to enhance system reliability.
• Tested Lustre-related monitoring products based on Docker containers developed by Cray.
• Participated in change control and release management processes for Lustre client and server.

Senior Systems Analyst Programmer (HPC Storage Systems Administrator) (Nov 2007 – Dec 2014)

• Assisted in the operation, maintenance, and administration of two production Lustre file systems for academic research computing using DDN hardware and Mellanox InfiniBand networks.
• Developed and utilized software for file system analysis, monitoring, and system automation.
• Deployed, administered, and monitored Linux systems for performance, security, stability, and errors.
• Performed extensive hardware validation and acceptance testing for new HPC cluster deployments.
• Administered and provided user support for OpenSFS Test Cluster for testing and development of OpenSFS funded Lustre development.
• Evaluated Lustre releases and associated tools using a Vagrant/VirtualBox VM testing and development environment I designed and implemented.
• Collaborated directly with research teams to implement scientific computing solutions.
• Provided direct support to all users through ticketing system and offered consultations for extended or complex projects.
• Created and presented documentation for users, including usage and best practices of Lustre file system.
• Tested, diagnosed, and improved Ethernet and Infiniband networking performance and reliability.
• Contributed to the evaluation, assessment, and procurement of software and hardware; evaluated early builds of Chroma/Intel Manager for Lustre.
• Worked with vendors to report and diagnose issues, including the replacement and repair of hardware.
• Executed critical data management and provided technology support for scientists in remote field deployments to Antarctica and Greenland in association with NASA and NSF (Operation IceBridge).

Student Systems Administrator (2001 – 2006)

• Provided system administration and hardware support for the Rosen Center for Advanced Computing (RCAC).
• Provided technical support to students, faculty, and staff of the Earth and Atmospheric Sciences Dept.