HPC Systems Engineer – Machine Learning Infrastructure & Operations
Core
Design, operate, and automate high-performance computing (HPC) infrastructure for machine learning workloads across four data centers, supporting research teams in training frontier-scale neural networks.
Role type
Senior HPC Systems Engineer (Infrastructure & Operations)
Builds
Production-grade HPC clusters, virtualization layers, storage backends, and automated operations pipelines for ML research.
Domain
High-Performance Computing (HPC) & Machine Learning Infrastructure
Deliverable
infrastructure
Required skills
Linux administration, HPC cluster management (Slurm), parallel file systems (Lustre/Ceph), GPU workload management, data-center networking (InfiniBand, Ethernet), Ceph storage operations, virtualization (Proxmox), infrastructure automation (Ansible), scripting (Bash/Python), containerization (Apptainer/Docker), monitoring (Prometheus/Grafana)
Preferred skills
LLM tooling (agent frameworks, tool calling, retrieval), AI agent integration for admin workflows
Technologies
Slurm, Lustre, Ceph, Proxmox, Ansible, InfiniBand, Apptainer, Prometheus, Grafana, NVIDIA CUDA/DCGM
Responsibilities
Design and operate HPC clusters across multiple data centers; manage heterogeneous compute, storage, and network nodes; run and extend virtualization clusters; operate and scale storage platforms; automate operations as code; build monitoring and alerting systems; plan hardware roll-outs and migrations; support users on efficient cluster usage.
Seniority
Senior, hands-on IC
