Cerebras Senior Software Development Engineer in Test (SDET) at Cerebras to develop test automation and validate complex AI inference systems. Own integration testing and release qualification for AI Inference Core features.
Responsibilities
We are looking for an experienced, hands-on Senior Software Development Engineer in Test (SDET) to join the Release Integration Testing (RIT) function within Release & Feature Qualification for AI Inference Core.
The Production Engine for Inference Core — turning integrated features into reliable production releases.
This is a highly technical, hands-on engineering role requiring strong software development, automation, and debugging skills. You will independently own complex testing initiatives, contribute to test architecture and release qualification strategies, and collaborate closely with engineering teams to improve system reliability.
Release Integration Testing (RIT) is the bridge between feature qualification and release qualification. Feature teams retain ownership of feature design, feature-level qualification, and feature regression. RIT focuses on integration readiness, cross-stack validation, regression stability, and first-pass rollout triage for AI Inference Core.
What Makes This Role Distinct
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.
Design, develop, and maintain automated test frameworks, tools, and infrastructure to validate AI inference software across multiple components and system layers.
Qualification
Experience with AI/ML infrastructureExposure to hardware acceleratorsFamiliarity with performance testingExperience with containers
Preferred
Experience testing or developing distributed systems, infrastructure software, runtime systems, compilers, kernels, or other low-level software.
Experience with AI/ML infrastructure, LLM inference, model deployment, multimodal workloads, or large-scale compute environments.
Exposure to hardware accelerators, GPU systems, software/hardware integration, or high-performance computing.
Experience building scalable test frameworks, distributed test systems, release pipelines, or internal developer tools.
Familiarity with performance testing, profiling, observability, fault injection, reliability engineering, or production failure analysis.
Experience with containers, Kubernetes, cloud infrastructure, cluster orchestration, or large-scale distributed computing environments.
Experience using debugging and observability tools to diagnose complex system-level issues.
Experience working in fast-paced engineering environments, including startups or teams developing complex systems software.
