Senior Inference Platform SDET

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services.

This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation.

Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership https://openai.com/index/cerebras-partnership/ with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

About the Role

We are looking for an Inference Platform SDET to join the Inference Service Quality team at Cerebras and work on the inference platform. This team sits at the intersection of distributed systems, cloud and cluster infrastructure, and the software stack that serves the world's fastest AI inference.

In this role, you will own the quality and reliability of the infrastructure that deploys and runs the Cerebras Inference Platform — from CI/CD pipelines and Kubernetes-based deployments to ingress, load balancing, and service discovery. You will validate the platform both in cloud environments and on real Cerebras clusters, working side by side with the Inference Platform development team to catch issues before our customers do.

This is an excellent opportunity for engineers who enjoy infrastructure, automation, and debugging across the full deployment stack, and who want to ensure that a platform serving inference at massive scale stays fast, reliable, and production-ready.

Responsibilities

• Design, build, and maintain test infrastructure and automation for deploying and validating the Cerebras Inference Platform.

• Validate the platform across environments — from cloud-managed Kubernetes to deployments running on Cerebras hardware.

• Test and verify deployment infrastructure including Kubernetes workloads, CI/CD pipelines, ingress and service discovery, NGINX, and load balancing.