I'm a seasoned HPC Systems Architect with over 8 years of experience designing and implementing high-performance computing solutions. I specialize in building scalable, efficient systems that handle complex computational workloads across diverse fields.
My expertise spans cluster architecture, parallel computing frameworks, storage systems, and performance optimization. I work closely with researchers, and students to deliver HPC solutions that accelerate scientific discovery and innovation.
When I'm not optimizing compute clusters or benchmarking systems, you can find me contributing to open-source HPC projects, attending supercomputing conferences, or exploring the latest developments in scientific computing and machine learning.
HPC Cluster Design, Network Topology, Storage Architecture, and Scalable Infrastructure Planning
Code Profiling, Parallel Computing, Resource Management, and Workload Scheduling
Parallel File Systems, High-Speed Networks, and Data Management Solutions
System Monitoring, Performance Analysis, Capacity Planning, and Predictive Maintenance
Redesigned existing HPC cluster to leverage a "Pod" architecture to segregate especially high power and high heat workloads to better leverage power and cooling in existing datacenter space.
Lead a team in migrating from legacy provisioning and management techniques to leveraging Warewulf for cluster management and provisioning, resulting in extremely quick maintenance periods with minimal downtime.
Built Lustre based storage system from comodity hardware to provide scalable, single namespace storage for campus compute cluster.