Cloud Quality Engineer

The role

You will own weekly cloud releases end to end and build scalable test infrastructure for the Inference Cloud platform. You will work across the full stack including client SDK, API, gateway, inference software, driver, and hardware.

What you will do

• Drive weekly cloud release qualification end to end.
• Build and evolve functional, integration, performance, and fault test infrastructure.
• Reason through the full stack from client SDK to hardware.
• Read and review developer PRs to understand impact and blast radius.
• Increase automation coverage continuously and fix flaky tests.
• Use AI tooling to accelerate test creation, debugging, and analysis.
• Drive team standards for testing and release readiness.
• Work with platform, ML, infrastructure, and product teams across timezones.

Required qualifications

• 5+ years of experience in quality engineering, test engineering, or a closely related role.
• Substantial individual contributor experience on large-scale distributed systems or cloud infrastructure.
• Deep cloud platform experience.
• Track record of building scalable test infrastructure.
• Strong systems debugging and reasoning.
• Strong proficiency in at least one backend language (Python, Go, or C++).
• Excellent written and async communication.
• Self-direction under ambiguity.

Nice to have

• AWS experience.
• Experience with Cloud infrastructure, model serving systems, or GPU accelerated workloads.
• Experience using AI tooling (LLMs, coding assistants, agents) to accelerate test development, triage, or analysis.

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.