AI Inference Core - SDET Technical Lead, Release Integration Testing

Cerebras Systems

4d•Hybrid

About The Position

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.

Requirements

Strong software-engineering fundamentals and programming ability in Python, C++, Go, or a similar language.
Demonstrated technical leadership in software quality, test infrastructure, systems validation, release engineering, or complex software integration.
Experience designing automation and test architecture for distributed, systems-level, infrastructure, or AI software.
Proven ability to break down ambiguous cross-stack failures, form hypotheses, gather evidence, and drive issues to resolution.
Strong understanding of risk-based testing, release readiness, regression strategy, failure analysis, and quality metrics.
Ability to influence and align multiple engineering teams without relying solely on organizational authority.
Clear communication and sound judgment during high-pressure release situations, including the ability to explain technical risk to engineering and leadership audiences.

Nice To Haves

Experience with software/hardware co-design, hardware accelerators, compilers, kernels, runtimes, or low-level systems.
Experience with AI infrastructure, model deployment, LLMs, multimodal workloads, or large-scale compute clusters.
Experience building test frameworks, distributed test systems, release pipelines, dashboards, or internal developer tooling.
Experience with performance testing, profiling, observability, fault injection, reliability, or production failure analysis.
Experience in a startup or similarly fast-moving, resource-constrained engineering environment.
Track record of taking a quality or release capability from zero to one and scaling it across teams.
Familiarity with containers, cluster orchestration, cloud infrastructure, CI/CD, or high-performance computing.

Responsibilities

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, coordinate owners through resolution, drive RCA, place missing coverage at the correct layer, and plan rollout across multiple product and release projects.
Partner with and mentor SDETs, feature teams, Integration, Core Infra, release owners, and deployment teams; between active engagements, advance automation efficiency, diagnostics, probes, and roadmap test planning.