Key skills
PythonJavaGoSQLNoSQLAIMLGenerative AIMLOpsAWSAzureGCPTerraformKubernetesDockerJenkinsGitHub ActionsAnsibleArgoCDCloudFormationRedisPrometheusGrafanaDatadogELK StackGitHubMemcachedCachingCI/CDChange Management
About this role
SambaNova is building the future of AI computing, focusing on generative AI and high-performance computing. As a Senior Cloud Site Reliability Engineer, you will ensure the reliability and performance of the AI Inferencing Service, bridging the gap between software development and operations.
Responsibilities:
- Take shared ownership of the production inferencing service, including its availability, latency, performance, efficiency, change management, monitoring, emergency response, and capacity planning across multiple regions
- Participate in a balanced on-call rotation to provide 24/7 support for the service
- Lead the response to incidents affecting the inferencing service, driving blameless post-mortems and implementing corrective actions to prevent recurrence
- Develop and maintain advanced monitoring, alerting, and dashboarding (using tools like Prometheus, Grafana, Datadog) to gain deep insights into service health, model performance (e.g., latency, throughput, error rates), and accelerator utilization
- Proactively identify and eliminate performance bottlenecks
- Design and implement auto-scaling policies to handle variable inference loads cost-effectively
- Manage and evolve our cloud infrastructure (on AWS, GCP, and/or Azure along with on-prem) using tools like Terraform and Ansible, ensuring it is secure, repeatable, and scalable
- Champion automation by building and improving CI/CD pipelines for the seamless and safe deployment of new model versions and service updates
- Forecast infrastructure needs based on product roadmaps and usage trends
- Work with finance and engineering teams to manage cloud costs and optimize spending
- Define, measure, and report on Service Level Objectives (SLOs) and Indicators (SLIs) for the inferencing platform, using data to drive prioritization and reliability investments
Requirements:
- Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience
- 5-8+ years of experience in a Site Reliability Engineer, DevOps, or related role supporting a large-scale, customer-facing service in a public cloud environment (AWS, GCP, Azure)
- Strong programming/scripting skills in languages like Python, Go, or Java
- Proven experience with containerization and orchestration technologies (Docker, Kubernetes)
- Deep understanding of monitoring and observability principles and tools (e.g., Prometheus, Grafana, ELK Stack, Datadog)
- Solid experience with Infrastructure as Code (e.g., Terraform, CloudFormation)
- Familiarity with CI/CD principles and tools (e.g., Jenkins, GitHub Actions, ArgoCD)
- Excellent problem-solving skills and a systematic approach to troubleshooting complex distributed systems
- Experience in a hybrid environment bridging cloud and on-premise/data center infrastructure
- Direct experience supporting ML/AI inferencing services in production
- Familiarity with GPU-accelerated computing and optimizing workloads for NVIDIA GPUs for purposes of mapping to RDUs
- Knowledge of model serving frameworks like vLLM, SGLang or Ray
- Understanding of MLOps principles and practices
- Experience with managing and tuning databases (SQL or NoSQL) and caching systems (Redis, Memcached)
- Strong Linux/Unix system administration fundamentals