Cloud Site Reliability Engineer

Responsibilities

• Take shared ownership of the production inferencing service, including availability, latency, performance, and capacity planning
• Participate in a balanced 24/7 on-call rotation to provide service support
• Develop and maintain advanced monitoring, alerting, and dashboarding using tools like Prometheus, Grafana, and Datadog
• Design and implement auto-scaling policies and eliminate performance bottlenecks
• Manage and evolve cloud infrastructure on AWS, GCP, and Azure using Terraform and Ansible
• Build and improve CI/CD pipelines for seamless deployment of model versions and service updates
• Define, measure, and report on Service Level Objectives (SLOs) and Indicators (SLIs)

Requirements

• Bachelor's degree in Computer Science, Engineering, or a related field
• 3-5+ years of experience in SRE, DevOps, or a related role supporting large-scale public cloud services
• Strong programming/scripting skills in Python, Go, or Java
• Proven experience with Docker and Kubernetes
• Deep understanding of monitoring and observability tools (Prometheus, Grafana, ELK Stack, Datadog)
• Solid experience with Infrastructure as Code (Terraform, CloudFormation)
• Familiarity with CI/CD tools (Jenkins, GitHub Actions, ArgoCD)
• Strong troubleshooting skills for complex distributed systems

Preferred Qualifications

• Experience in hybrid environments bridging cloud and on-premise infrastructure
• Direct experience supporting ML/AI inferencing services in production
• Familiarity with GPU-accelerated computing and NVIDIA GPU optimization
• Knowledge of model serving frameworks like vLLM, SGLang, or Ray
• Understanding of MLOps principles and practices
• Experience managing SQL/NoSQL databases and caching systems like Redis

About the Company

SambaNova Systems is building the future of AI computing with an integrated hardware and software platform. Their SambaNova Suite is a full-stack generative AI platform optimized for enterprise and government organizations.