Senior Software Engineer, Inference Cloud

The role

This individual contributor will build cloud services and Kubernetes infrastructure. You will design cloud components, improve request routing, work with production databases, and debug issues across the stack.

What you will do

• Build and improve production Kubernetes environments on Amazon EKS.
• Own improvements to workload scheduling, autoscaling, cluster upgrades, resource utilization, network policies, and failure recovery.
• Develop and operate traffic management infrastructure using Envoy and Istio.
• Improve routing, rate limiting, connection management, timeouts, retries, and failover.
• Build database-backed services and improve the reliability and performance of data stores.
• Troubleshoot query performance, connection pooling, and availability issues.
• Identify bottlenecks across applications, Kubernetes, networking, and databases.
• Automate infrastructure provisioning and application delivery using Terraform, Argo CD, and Kustomize.
• Build actionable metrics, logs, traces, dashboards, and alerts.
• Investigate incidents and contribute to design reviews and code reviews.

Required qualifications

• 5+ years of software engineering experience, including building and operating production services or cloud infrastructure.
• Strong Kubernetes expertise, including workload lifecycle, networking, service discovery, storage, autoscaling, and troubleshooting cluster and application failures.
• Hands-on experience with Amazon EKS or a comparable managed Kubernetes service.
• Experience configuring and troubleshooting Envoy and Istio, or comparable proxy and service mesh technologies.
• Solid understanding of HTTP, gRPC, DNS, TLS, and mTLS.
• Experience developing services that use production databases, with practical knowledge of query optimization, indexing, connection management, and database reliability.
• Strong programming skills in Go or another backend or systems language.
• Experience with infrastructure as code and automated deployment workflows using Terraform, Argo CD, Kustomize, or equivalent tools.
• Experience diagnosing performance and reliability issues using metrics, logs, and tracing.
• Ability to independently deliver projects, explain technical tradeoffs, and collaborate effectively across engineering teams.

Nice to have

• AWS networking experience, including VPNs, Transit Gateway (TGW), Direct Connect (DX), VPC routing, and security groups.
• Experience designing distributed systems, including replication, consistency, fault tolerance, and multi-region operation.
• Production programming experience in C++.
• Experience optimizing latency, throughput, and efficiency in high-QPS systems.
• Experience reducing time to first token (TTFT) and tail latency is a strong plus.
• Familiarity with ML inference infrastructure or model serving systems.

About the company

Cerebras Systems builds the world's largest AI chip. The company works with leading model labs, global enterprises, and cutting-edge AI-native startups.