// Software & Systems Engineer
Brady Bangasser
I build and operate large-scale systems to stay fast, available, and secure, across HPC, multi-cloud infrastructure, and the automation that ships them.
// focus areas
Reliability & Platform
High-availability systems, observability, and self-healing infrastructure built to survive failure - not just avoid it.
Cloud & Infrastructure
Multi-cloud and on-prem infrastructure as code, least-privilege IAM, and security hardened to recognized standards.
HPC & Distributed Systems
Cluster operations at scale - SLURM and Kubernetes scheduling, performance tuning, and distributed workloads.
Systems & Security
Low-level performance work, compiler and toolchain internals, and applied cryptography and authentication.
// projects
view all →zkRP: Encrypted P2P with Zero-Knowledge Range Proofs
An encrypted peer-to-peer network of APIs and services built on zero-knowledge range proofs, operated to a 99.9% SLO.
Erid: Unified Hybrid-Cloud Images
One Packer pipeline producing identical golden images across on-prem and AWS, plus the mTLS control plane and mesh that run my hybrid cloud in production.
FratRat
A privacy-first dating app for college students, built on zkRP's encrypted peer-to-peer network, with the goal of an isolated network per university.
// writing
view all →PEARC26: what a poster judge learns about running research computing
Notes from PEARC26 in Minneapolis on judging student work, hybrid Slurm and Kubernetes scheduling, and a login-node idea I want to build.
Building a rootless edge: Traefik, Podman, and per-container TLS
How I built a self-registering reverse proxy on rootless Podman with per-domain TLS, a private CA, and multi-cloud portability, and where I chose it over Kubernetes.
Notes on job scheduling in HPC clusters
A deeper look at how scheduling policy shapes throughput and fairness on shared clusters.