2 days ago
Base Salary
$140k - $178k/yr
Responsibilities
- Lead architecture, hardware qualification, capacity planning, and maintenance for large-scale bare-metal NVIDIA and AMD GPU clusters.
- Design multi-tenant compute and control planes across Kubernetes, Red Hat OpenShift, and HPC cluster managers.
- Optimize high-throughput, low-latency RDMA and RoCEv2 network fabrics.
- Architect infrastructure-as-code and GitOps automation using Ansible, Terraform, Python, Go, and CI/CD tooling.
- Oversee automation for firmware, BIOS/BMC configuration, kernel drivers, platform upgrades, and certificate rotations.
- Optimize distributed workload scheduling, fair-share queueing, and GPU quota governance across Slurm, Kueue, Volcano, and Ray.
- Profile systems performance and diagnose interconnect, bandwidth, memory, compute, GPU, driver, and hardware issues.
- Establish observability standards using OpenTelemetry, Prometheus, and Splunk, including dashboards and anomaly detection.
- Lead high-impact incident escalations and root-cause analyses while authoring architecture blueprints and standard operating procedures.
- Mentor and coach mid-level and senior engineers.
Requirements
- Bachelor’s degree in Computer Science, Engineering, IT, or a related discipline.
- 5+ years of progressive experience in enterprise systems engineering, HPC, AI infrastructure, or SRE.
- Proficiency in Python, Go, or Bash and extensive experience with Ansible, Terraform, CI/CD, and GitOps automation.
- Advanced experience designing and administering production Kubernetes, Red Hat OpenShift, and HPC workload managers including Slurm, Kueue, Volcano, and Ray.
- Strong hands-on knowledge of AI backend network fabrics, RDMA, RoCEv2, and high-speed network topologies.
- In-depth knowledge of enterprise Linux, kernel module lifecycles, memory subsystems, GPU drivers, Redfish, and IPMI.
- Preferred: master’s degree or an additional 2+ years of equivalent specialized engineering experience.
- Preferred: 3+ years managing enterprise server platforms at scale, including environments with 500+ nodes.
- Preferred: 2+ years deploying, troubleshooting, and optimizing NVIDIA CUDA and AMD ROCm GPU software stacks.
- Preferred: 3+ years designing enterprise secrets management and identity federation architectures using technologies such as HashiCorp Vault, OIDC, SAML, and SSO.
- Preferred: an active advanced industry certification such as CKA/CKS, RHCA/RHCE, or an advanced networking credential.
- Preferred: verifiable contributions to open-source infrastructure, Kubernetes SIGs, HPC scheduling communities, or telemetry frameworks.
Benefits
- The posted starting salary range is $140,300.00 to $178,100.00, excluding incentive compensation, equity, and benefits.
- Benefits may include medical, dental, vision, 401(k) matching, parental leave, disability coverage, life insurance, restricted stock units, paid holidays, vacation or flexible time off, sick time, wellness days, birthday leave, volunteer days, and annual bonuses.
- The application window is expected to close on November 22, 2026.
About Cisco
Cisco designs and sells networking, security, and collaboration platforms for enterprises, service providers, and governments, spanning routers and switches, Wi‑Fi, firewalls, zero‑trust, observability, and cloud-managed IT (Meraki) plus Webex. Its business model mixes hardware, software subscriptions, and support/consulting services. Founded in 1984 and headquartered in San Jose, California, Cisco is a public company traded on Nasdaq and serves customers across data centers, campuses, and service provider networks.