Cerebras
Senior Software Engineer, Inference Cloud
Sunnyvale, CA · On-site · Senior · Full-time · Posted Jul 12, 2024
- Experience
- 5+ years of software engineering experience, including building and operating production services or cloud infrastructure.
About the job
Build and operate the cloud services and Kubernetes infrastructure behind Cerebras’s Inference Service, focusing on reliability, latency, and global scale.
What you'll do
- Build and improve production Kubernetes environments, service networking, and traffic management.
- Develop database-backed services and improve performance, reliability, and recovery across the stack.
- Automate infrastructure and deployments, operate production systems, and investigate incidents with cross-functional teams.
What they ask for
- Strong Kubernetes expertise and hands-on experience with Amazon EKS or a comparable managed Kubernetes service.
- Experience configuring and troubleshooting Envoy and Istio or comparable technologies, with knowledge of HTTP, gRPC, DNS, TLS, and mTLS.
- Experience developing production services that use databases and diagnosing performance or reliability issues.
- Strong programming skills in Go or another backend or systems language; experience with infrastructure as code and automated deployment workflows.
Nice to have
- AWS networking experience; distributed systems design; production C++ experience.
- Experience optimizing high-QPS systems, reducing TTFT or tail latency, or working with ML inference infrastructure.
Tools
Kubernetes, Amazon EKS, Envoy, Istio, Terraform, Argo CD, Kustomize, Go
AI focus
Build and operate cloud infrastructure for AI model inference services; familiarity with ML inference infrastructure or model serving is preferred.
Model-written summary · the original posting is authoritative