Staff Test & Release Engineer, Inference Cloud - Santa Clara, United States

Originally posted 15 October 2026 by the employer.

Own how software for d-Matrix’s inference services is tested end to end and released, focusing on the Inference Cloud platform.

About the role

The Staff Test & Release Engineer will own how software for d-Matrix’s inference services is tested end to end and how it is released, specifically for the Inference Cloud platform.

What you'll do

• Design and build end-to-end test infrastructure for Inference Cloud that stands up homogeneous and heterogeneous inference deployments on demand, runs tests against them, and tears them down.
• Turn user stories and acceptance criteria into automated end-to-end tests, including failure cases.
• Bring real hardware into CI by running tests on GPU and Corsair nodes, scheduling fairly on a limited shared pool, and owning test-signal quality.
• Own the release strategy for the orchestration platform, Kubernetes tooling, and benchmarking tools, including versioning, cadence, branching, promotion, rollback, release notes, and go/no-go criteria.
• Lead the move from a single platform-wide release to independently released components, defining the component breakdown, cadence, versioning, and compatibility and upgrade testing.
• Define release gates covering functional tests, upgrade and compatibility tests, model accuracy evals, and performance baselines.

What you'll need

• 6+ years in test infrastructure, software engineering in test, release engineering, or a closely related role, including owning end-to-end testing or releases for a distributed system.
• Track record of building test or release automation that measurably improved release reliability or speed.
• Experience running test and release infrastructure across on-premises clusters and a public cloud, preferably Azure (AKS, Azure DevOps or GitHub Actions on Azure, Azure networking and identity).
• Strong Kubernetes experience, including deploying and debugging multi-service workloads, Helm, operators and custom resources, and automated test cluster setup and teardown.
• Experience designing CI/CD pipelines (such as GitLab CI, GitHub Actions, Buildkite, or Argo), including artifact versioning, environment promotion, and rollback.
• Proficiency in Python and pytest or a comparable framework, plus fluency in a second language sufficient to read and test the code under qualification.
• Experience testing on shared, limited hardware such as GPU or accelerator fleets, accounting for scheduling, contention, and hardware faults.
• Sound judgment about what to test end to end versus lower in the stack, and the ability to explain tradeoffs to code owners.
• Record of building consensus across teams and turning input into a strategy people follow.
• Fluency with AI and agentic tools for writing tests, triaging failures, and searching logs and code, with the discipline to verify their output.

Nice to have

• Experience testing or releasing LLM serving systems such as vLLM, SGLang, or TensorRT-LLM, including accuracy evals (such as GSM8K, HumanEval, MMLU) and performance benchmarks as release gates.
• Familiarity with speculative decoding, disaggregated serving, or heterogeneous inference.
• Hardware-in-the-loop testing experience, including qualifying software across driver, firmware, and hardware versions.
• Experience with operator and controller testing tools such as envtest, kuttl, or chainsaw, and with upgrade and CRD version-migration testing.
• Experience shipping software into customer-managed, on-premises Kubernetes environments, including compatibility matrices and customer install packaging.
• Experience with canary or progressive rollouts for customer-facing services.
• Rust experience.
• Startup experience or comfort in environments where priorities shift quickly.

Skills: end-to-end test infrastructure, Inference Cloud, Kubernetes, CI/CD pipelines, LLM serving systems