Staff Test & Release Engineer – Inference Cloud

d-Matrix

. Design and build end-to-end test infrastructure for Inference Cloud .

Posted 10/15/2026full-timeSanta Clara • California • United StatesLead💰 $155,000 - $235,000 per yearWebsite

Tech Stack

Tools & technologies

AzureCloudKubernetesPythonRust

About the role

Key responsibilities & impact

Design and build end-to-end test infrastructure for Inference Cloud
Stand up homogeneous and heterogeneous inference deployments on demand, run tests, and tear them down
Convert user stories and acceptance criteria into automated end-to-end tests, including failure cases
Run tests on GPU and Corsair nodes in CI
Schedule fairly on a limited shared hardware pool
Own test-signal quality, flaky tests, and routing failures to the right owner
Own release strategy for the orchestration platform, Kubernetes tooling, and benchmarking tools
Define versioning, cadence, branching, promotion, rollback, release notes, and go/no-go criteria
Lead the transition from platform-wide releases to independently released components
Define release gates for functional tests, upgrade and compatibility tests, model accuracy evaluations, and performance baselines
Partner with QE, product, platform, and infrastructure teams on shared test strategy
Enable feature engineers to write and own tests
Build testing and release systems for d-Matrix’s internal and customer-facing inference cloud, using on-premises clusters and Azure

Requirements

What you’ll need

6+ years in test infrastructure, software engineering in test, release engineering, or a closely related role
Experience owning end-to-end testing or releases for a distributed system
Track record of building test or release automation that improved release reliability or speed
Experience across on-premises clusters and a public cloud, preferably Azure
Strong Kubernetes experience, including multi-service workloads, Helm, operators, custom resources, and automated cluster setup and teardown
Experience designing CI/CD pipelines, artifact versioning, environment promotion, and rollback
Proficiency in Python and pytest or a comparable framework
Fluency in a second programming language sufficient to read and test code
Experience testing shared, limited GPU or accelerator hardware fleets
Sound judgment about end-to-end versus lower-level testing
Experience building consensus across teams and turning input into strategy
Fluency with AI and agentic tools for writing tests, triaging failures, and searching logs and code
Preferred: Experience with LLM serving systems such as vLLM, SGLang, or TensorRT-LLM
Preferred: Familiarity with speculative decoding, disaggregated serving, or heterogeneous inference
Preferred: Hardware-in-the-loop testing
Preferred: envtest, kuttl, or chainsaw
Preferred: Customer-managed, on-premises Kubernetes environments
Preferred: Canary or progressive rollouts
Preferred: Rust experience
Preferred: Startup experience or comfort with shifting priorities
Legally authorized to work in the United States

Benefits

Comp & perks

Equity
Bonus
Medical insurance
Dental insurance
Vision insurance
401(k)
Incentive opportunities based on individual and company performance
Benefits package centered around employee and loved-ones wellbeing