Senior AI Inference Cloud Platform Engineer

SambaNova; Austin (TX); On-site; USD 144,000 - 189,000; Full time

Benefits offered by this job

Health insurance

HSA with employer contribution

Dental, Vision

Headspace subscription

Gympass+ membership

Job summary

SambaNova Systems is seeking a Principal Cloud Platform Engineer to own the AI inference service reliability, latency, and scalability. You will bridge software and operations, ensuring uptime and efficient resource use, with on-call rotation for 24/7 support.

You will automate infrastructure in new regions, build monitoring, and drive CI/CD for model updates while collaborating with finance on cloud spend. Strong SRE/DevOps and cloud experience are essential.

Qualifications

• B.S. in Computer Science, Computer Engineering, or related field.
• 3+ years of Site Reliability Engineering or DevOps experience.
• Experience supporting a large-scale customer-facing service in a public cloud environment (AWS, GCP, Azure).
• Strong programming in Python, Go, Rust, or Java.
• Proven experience with containerization and orchestration (Docker and Kubernetes).
• Deep understanding of monitoring/observability tools (Prometheus, Grafana, Datadog, ELK).
• Experience with Infrastructure as Code (Terraform, CloudFormation).
• Experience with CI/CD (Jenkins, GitHub Actions, ArgoCD).
• Strong Linux/Unix system administration fundamentals.

Responsibilities

• Own production inferencing service reliability across regions including availability, latency, and performance.
• Automate AI infrastructure provisioning in new regions.
• Participate in on-call rotation and lead incident response.
• Build monitoring dashboards (Prometheus, Grafana, Datadog) for health, latency, throughput, and accelerator usage.
• Identify and eliminate performance bottlenecks; design auto-scaling policies.
• Manage infrastructure as code (Terraform, Ansible) and CI/CD pipelines for model deployments.
• Forecast infra needs, align with product roadmap, and collaborate with finance on cloud spend.
• Define and report SLOs/SLIs for the inferencing platform.

Skills

SRE/DevOps experience

Public cloud (AWS/GCP/Azure)

Python/Go/Rust/Java

Docker & Kubernetes

Terraform/CloudFormation

CI/CD (Jenkins/GitHub Actions/ArgoCD)

Linux/Unix administration

Education

B.S. in Computer Science/Computer Engineering or related field

Tools

Prometheus

Grafana

Datadog

ELK Stack

Terraform

CloudFormation

Jenkins

GitHub Actions

ArgoCD

Docker

Kubernetes

Job description

SambaNova Systems is seeking a Principal Cloud Platform Engineer to own the AI inference service reliability, latency, and scalability. You will bridge software and operations, ensuring uptime and efficient resource use, with on-call rotation for 24/7 support.

You will automate infrastructure in new regions, build monitoring, and drive CI/CD for model updates while collaborating with finance on cloud spend. Strong SRE/DevOps and cloud experience are essential.