The opportunity
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.
What you'll do
Software engineering applied to quality: Design and develop scalable test automation, frameworks, diagnostics, and tooling to validate complex AI inference systems—not just execute test cases.
Cross-stack technical challenges: Debug and validate interactions across AI frameworks, runtime, compiler, kernels, distributed systems, infrastructure, and hardware.
Integration and release ownership: Independently drive integration testing, regression validation, and release qualification activities for complex inference-core features.
Inference-path validation: Identify and test high-risk interactions across runtime, host, device programming, memory, scheduling, and model execution.
Production reliability: Improve master and release-branch stability through robust automation, failure analysis, and actionable quality metrics.
Technical collaboration: Partner with SDETs, software engineers, infrastructure teams, and release owners to resolve complex issues and improve engineering efficiency.
What they're looking for
- Design, develop, and maintain automated test frameworks, tools, and: infrastructure to validate AI inference software across multiple components and system layers.
- Independently own integration testing and qualification activities for: complex inference-core features, identifying dependencies, interaction risks, and potential coverage gaps.
- Develop and execute comprehensive end-to-end, integration, regression, and: system-level tests across AI frameworks, runtime, compiler, kernels, infrastructure, and hardware.
- Analyze unit, simulation, benchmark, feature-test, and integration results to: assess readiness, identify gaps, and provide evidence-based recommendations for release qualification.
