Senior SDET, Inference Platform

About the role

Cerebras Systems builds the world's largest AI chip, delivering training and inference speeds over 10 times faster than GPU-based cloud services. It is looking for an Inference Platform SDET to join the Inference Service Quality team and 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. The role validates the platform in cloud environments and on real Cerebras clusters, working with the Inference Platform development team.

Key responsibilities

• Design, build and maintain test infrastructure and automation for deploying and validating the Inference Platform.
• Validate the platform across environments, from cloud-managed Kubernetes to deployments on Cerebras hardware.
• Test and verify Kubernetes workloads, CI/CD pipelines, ingress, service discovery, NGINX and load balancing.
• Collaborate with the Inference Platform development team so new features ship reliably.
• Investigate and debug complex issues spanning networking, orchestration, deployment and distributed services.
• Develop and maintain testbeds for performance, scalability and reliability validation.
• Identify failure points, bottlenecks and edge cases affecting stability and inference performance.
• Contribute to test plans and validation strategies for new features and releases.
• Improve observability, diagnostics and debugging workflows, and partner with engineering teams on production-ready releases.

Required profile

• 3+ years of experience in software engineering, QA, systems engineering or infrastructure development.
• Hands-on experience debugging complex systems, distributed services or networked infrastructure.
• Familiarity with systems-level development, infrastructure tooling or platform integration.
• Strong problem-solving, communication and collaboration skills.
• Mentoring junior engineers is preferred.

Required skills

• Strong programming in Python and/or Go (both a plus).
• Building automation tools, testing frameworks or internal developer tooling.
• CI/CD systems such as Jenkins.
• Preferred: Kubernetes and container orchestration, cloud-managed Kubernetes (Amazon EKS), GitOps tooling (e.g. ArgoCD), ingress controllers, NGINX, load balancing, Bazel, k9s, performance debugging and ML inference infrastructure.