Senior Inference Platform QA Engineer

Cerebras; United States; On-site; USD 150,000 - 190,000; Full time

Job summary

Cerebras Systems is seeking an Inference Platform SDET to join the Inference Service Quality team. You will own the quality and reliability of the Cerebras Inference Platform—from CI/CD pipelines and Kubernetes deployments to ingress, load balancing, and service discovery.

You will validate across cloud environments and Cerebras hardware, collaborating with the platform development team to catch issues before customers do.

Qualifications

• 5+ years of software engineering, QA, or infra experience.
• Strong Python and/or Go programming abilities.
• Experience with automation, testing frameworks, or internal tooling.
• Hands-on CI/CD experience (e.g., Jenkins).
• Experience debugging distributed systems and networks.
• Excellent communication and collaboration skills.
• Experience mentoring junior engineers.

Responsibilities

• Design, build, and maintain test infra and automation for deploying and validating the Cerebras Inference Platform.
• Validate the platform across cloud Kubernetes and Cerebras hardware deployments.
• Test deployment infra including Kubernetes workloads, CI/CD, ingress, and service discovery.
• Collaborate with the Inference Platform team to ensure reliable feature releases.
• Investigate and debug complex issues across networking, orchestration, and deployment.
• Develop testbeds to validate platform performance, scalability, and reliability.
• Identify failure points and edge cases impacting stability and inference performance.
• Contribute to test plans and validation strategies for new platform features.
• Improve observability and debugging workflows across the stack.
• Partner with eng teams to deliver production-ready releases.

Skills

Python

Go

CI/CD

Troubleshooting

Distributed systems

Mentoring

Debugging

Communication

Tools

Kubernetes

NGINX

ArgoCD

Bazel

k9s

Job description

Cerebras Systems is seeking an Inference Platform SDET to join the Inference Service Quality team. You will own the quality and reliability of the Cerebras Inference Platform—from CI/CD pipelines and Kubernetes deployments to ingress, load balancing, and service discovery.

You will validate across cloud environments and Cerebras hardware, collaborating with the platform development team to catch issues before customers do.