The posting, in SambaNova's own words
archived Oct 26, 2026SambaNova is a leader in next-generation AI infrastructure, delivering a full-stack inference platform for customers worldwide. At the core of SambaNova's technology is the RDU (Reconfigurable Dataflow Unit) — a chip built on a dataflow architecture rather than the traditional GPU model. Its decode performance is especially strong for agentic workloads like multi-turn agents, code generation, and long-running applications. RDUs are packaged into SambaRack, rack-scale hardware that lets customers deploy state-of-the-art models with better performance, greater energy efficiency, and faster time to value.
About the team
The Cloud Platform team owns the production inferencing service that serves SambaNova's models to customers on RDU accelerators, including capacity planning, deployment, monitoring, and incident response across regions in the United States, Asia, Europe, and Latin America.
Read the full posting ↓
About the role
As a Senior Principal Cloud Platform Engineer you'll keep our AI inferencing platform reliable, fast, and scalable. Your focus is uptime, latency, and resource utilization on the inference endpoints customers depend on. The work spans monitoring, deployment, capacity planning, and incident response, and includes a shared on-call rotation covering 24/7 coverage.
Responsibilities
Owning the availability, latency, and efficiency of the production inferencing service, including change management, emergency response, and standing up AI infrastructure in new regions Building and maintaining monitoring, alerting, and dashboards in Prometheus, Grafana, and Datadog covering service health, model latency and throughput, and RDU utilization Leading incident response, running blameless post-mortems, and automating the toil those incidents expose Finding and fixing performance bottlenecks, and designing auto-scaling policies that handle variable inference load without overspending Managing cloud and on-prem infrastructure as code in Terraform and Ansible, and building the CI/CD pipelines that deploy new model versions and service updates Required Qualifications B.S. in Computer Science, Computer Engineering, or related field, or equivalent practical experience 3+ years in a Site Reliability Engineering, , or related role supporting a large-scale, customer-facing service in a public cloud environment (AWS, GCP, Azure) Strong programming and scripting skills in Python, Go, or Java Production experience with and Kubernetes Deep understanding of monitoring and observability tooling such as Prometheus, Grafana, Datadog, or the ELK Stack Experience with infrastructure as code using or CloudFormation Experience with tooling such as Jenkins, GitHub Actions, or ArgoCD Strong Linux system administration fundamentals Preferred Qualifications Experience in a hybrid environment spanning cloud and on-premise data center infrastructure Experience supporting ML or 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 such as vLLM, SGLang, or Ray Experience managing and tuning databases (SQL or NoSQL) and caching systems such as Redis or Memcached