Senior Kubernetes Engineer – GPU & HPC Platform

NorthMark Compute & Cloud; Dallas (TX); Vor Ort; USD 130.000 - 180.000; Vollzeit

Benefits dieser Stelle

Company-Paid lunch stipend

Medical, dental, vision benefits

401(k) matching up to 6%

Paid parental leave

Zusammenfassung

NorthMark Compute & Cloud in Dallas seeks a Senior Kubernetes Engineer to design and operate GPU-accelerated container platforms at scale for AI/ML, HPC and LLM training. You will enable high-performance workloads across hybrid or on-prem environments with deep NVIDIA and Kubernetes expertise.

You will implement GPU scheduling, device plugins, MIG, and custom operators, while ensuring security, observability, and CI/CD through GitOps workflows and IaC tooling.

Qualifikationen

• Extensive Kubernetes production experience with GPU workloads.
• Experience with NVIDIA GPU Operator and device plugins.
• Proficiency in Go or Python for operator development.
• Knowledge of CRDs, RBAC, and scheduler extensions.

Aufgaben

• Architect Kubernetes clusters optimized for GPU workloads in on-prem or hybrid environments.
• Develop and maintain custom operators and controllers for automation.
• Integrate NVIDIA device plugins and MIG into scheduling layer.
• Tune scheduling with kube-scheduler plugins, Slurm, and Volcano.
• Collaborate with HPC/ML/DevOps teams for multi-tenant, high-throughput clusters.
• Drive observability with Prometheus, Grafana, OpenTelemetry.
• Enforce security using RBAC, OPA, or Gatekeeper.
• Maintain CI/CD pipelines for Kubernetes using GitOps (ArgoCD/FluxCD).
• Contribute to IaC using Terraform, Helm, and Kustomize.

Kenntnisse

Kubernetes

GPU scheduling

Go or Python

Tools

NVIDIA GPU Operator

NVML

MIG

DCGM

Prometheus

Grafana

OpenTelemetry

ArgoCD

FluxCD

Terraform

Helm

Kustomize

Jobbeschreibung

NorthMark Compute & Cloud in Dallas seeks a Senior Kubernetes Engineer to design and operate GPU-accelerated container platforms at scale for AI/ML, HPC and LLM training. You will enable high-performance workloads across hybrid or on-prem environments with deep NVIDIA and Kubernetes expertise.

You will implement GPU scheduling, device plugins, MIG, and custom operators, while ensuring security, observability, and CI/CD through GitOps workflows and IaC tooling.