FriendliAI
Software Engineer – Cloud Infrastructure
San Francisco · Hybrid · Full-time · Posted Aug 12, 2026
- Experience
- 5+ years designing, building, and operating large-scale Kubernetes infrastructure in production.
- Education
- Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
About the job
Design and operate the Kubernetes cluster platform and network infrastructure that supports FriendliAI’s GPU-accelerated inference cloud.
What you'll do
- Own multi-cluster, multi-tenant Kubernetes architecture, GPU scheduling, and inference-aware autoscaling.
- Build Kubernetes controllers, operators, and CRDs; manage the network data plane and cross-region connectivity.
- Define platform SLOs, improve reliability after incidents, and deliver infrastructure as code with Terraform, Helm, and GitOps.
What they ask for
- 5+ years designing, building, and operating large-scale Kubernetes infrastructure in production.
- Proven experience operating large-scale, high-traffic network services in production, with deep understanding of Kubernetes internals and cloud networking.
- Proficiency with AWS, Terraform, Helm, and Ansible.
- Programming skills in Go or Python, and strong debugging skills across distributed systems, containers, and Linux networking.
Nice to have
- Experience with Cilium and eBPF, GPU orchestration, or high-performance networking for distributed workloads.
- Experience with multi-cloud, hybrid-cloud, or bare-metal Kubernetes operations, or contributions to Kubernetes, Cilium, Istio, or other CNCF projects.
Tools
Kubernetes, AWS, Terraform, Helm, Ansible, Go, Python, Cilium
AI focus
Build and operate cluster infrastructure for GPU-accelerated AI inference, including GPU scheduling and autoscaling suited to inference traffic.
Model-written summary · the original posting is authoritative