AI Inference Core - SDET Technical Lead, Release Integration Testing

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. This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation. Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

We are looking for a hands-on SDET Technical Lead to establish and lead Release Integration Testing (RIT) within Release & Feature Qualification for AI Inference Core. The Production Engine for Inference Core — turning integrated features into reliable production releases. You will define the quality strategy across the pre-release and release cycle, from feature and model integration through branch stability, release qualification, deployment, and post-release learning. You will work across AI frameworks, runtime, compiler, kernels, distributed systems, infrastructure, and hardware to make release risk visible and actionable. This is a technical-leadership role, not a coordination-only position. You will design test architecture, lead difficult debugging and release decisions, mentor engineers, and write software and automation alongside the team. RIT is the bridge between feature qualification and release qualification. Feature teams retain ownership of feature design, feature-level qualification, and feature regression. RIT owns inference-core integration strategy, inference-path readiness approval, integrated cross-stack validation, and first-pass rollout triage. What Makes This Role Distinct Dedicated RIT ownership: Engage before feature qualification completes while keeping the boundary clear: feature teams own feature behavior and qualification; RIT owns integration strategy, readiness approval, integrated validation, and first-pass rollout triage. Inference-path readiness gate: Require evidence across unit, simulation, benchmark, feature, and integration testing, with explicit coverage gaps before release entry. Cross-stack test strategy: Define risk-based E2E and regression coverage for features spanning components, organizations, software layers, infrastructure, and hardware. Branch and rollout leadership: Establish measurable health standards for master and release branches, and coordinate inference-impacting rollout across multiple product and release projects. Hands-on technical authority: Lead through code, test architecture, difficult debugging, quality metrics, and evidence-based release decisions. Team multiplier: Raise the technical bar, mentor engineers, and align feature, infrastructure, integration, qualification, and release teams.

Define the RIT strategy, engagement criteria, ownership boundaries, entry and exit criteria, coverage expectations, and escalation thresholds for AI Inference Core. Engage early on high-risk inference changes; identify dependencies and interaction risks across runtime, host, device programming, memory, scheduling, model execution, infrastructure, and hardware. Own the inference-path readiness gate by reviewing unit, simulation, benchmark, feature-test, and integration evidence, documenting gaps, and approving integration readiness before release entry. Lead integrated inference E2E validation across features and the cloud-to-wafer stack; promote durable feature tests and add risk-based scenarios to release regression. Improve master and release-branch stability through actionable health metrics, failure classification, release-quality reporting, dashboards, qualification workflows, and release pipelines. Lead first-pass regression and rollout triage,