Administer and maintain large-scale HPC/AI environments, including compute, storage, networking, software stacks, and Slurm scheduling. Develop automation for provisioning, configuration, and monitoring; optimize systems for benchmarking, capacity planning, and performance. Support security patching, troubleshooting, application deployment, researcher support, documentation, vendor coordination, procurement, and lifecycle management. This remote or hybrid individual contributor role requires approximately four domestic trips annually and U.S. citizenship for access to government research facilities.

Profile and optimize HPC applications across architectures; identify bottlenecks, develop algorithmic and software solutions to accelerate workloads, translate application needs into software/hardware features, and build performance models for future architectures.

Lead porting and performance analysis of diverse HPC applications on novel architectures. Profile node- and scale-level bottlenecks, design algorithmic/software solutions, translate application needs into software and hardware features, and develop performance models for future hardware.