I’m a Computer Engineering student at Clemson. I administer our student HPC cluster, spent a summer building infrastructure at Los Alamos, and run the Kubernetes homelab serving this page.
Built a 10-node stateless HPC cluster with Slurm, automated provisioning with cloud-init and Ansible, and added GitLab CI/CD builds for boot images.
For a retrieval system serving 2 TB of scientific PDFs, I benchmarked five vector databases on 2.7 million embeddings. The selected backend delivered 20× the previous solution’s throughput in that workload.
Research poster accepted for presentation at SC26.
I co-built and administer our student team’s cluster with eight NVIDIA A100 GPUs. My work includes configuring distributed workloads, investigating scaling bottlenecks, and tuning performance.
Competed at SC25 and co-authored our reproducibility paper, including an evaluation of distributed graph algorithms across three nodes. Returning for SC26. I also built a 16-node Raspberry Pi cluster for the Single Board Cluster Competition.
Rocky Linux
Slurm
MPI
NVIDIA A100
The team at SC25 · St. LouisAt work during the competition
This website runs on three Lenovo mini PCs in my homelab. Ansible configures the Linux hosts; GitHub Actions tests and publishes the container image, and Argo CD deploys it from a digest pinned in Git.
I’ve added highly available control-plane services and replicated storage, and tested node failures and backup restores. Prometheus and Grafana help me inspect service health and resource usage.
A TCP client/server tool for measuring round-trip latency and sending throughput. It reports p95/p99 latency and handles partial transfers and interrupted socket calls.
Built a theft detection system across two NVIDIA Jetsons in 24 hours. We split object detection and facial recognition between devices and sent alerts to a web dashboard, with GPU inference running in Docker.
I’m studying Computer Engineering at Clemson, with a minor in Mathematical Sciences. I expect to graduate in May 2028; my current GPA is 3.9/4.0.
I’m interested in SRE, systems administration, platform engineering, infrastructure, DevOps, and HPC. The work I enjoy most is getting Linux machines configured, understanding how they communicate, and figuring out why a workload isn’t behaving as expected.
