Staff Test & Release Engineer, Inference Cloud

D-Matrix Corp.; Santa Clara (CA); Remote; USD 180,000 - 230,000; Full time

Job summary

d-Matrix is building the deployment and orchestration tech for inference services, spanning on-prem Corsair/GPU clusters and an Azure cloud. As Staff Test & Release Engineer, you own end-to-end testing and the release process, ensuring features are validated on hardware and delivered safely to customers.

You will extend test infra, partner with QE, product, platform and infra teams, and drive a move to independently released components with clear versioning, gates, and rollback plans.

Qualifications

• 6+ years in test infrastructure, software engineering in test, release engineering, or a closely related role.
• 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.
• 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 (Rust in our stack).
• Experience testing on shared, limited hardware such as GPU or accelerator fleets, accounting for scheduling and faults.
• Sound judgment about end-to-end vs lower-stack testing and the ability to explain tradeoffs to code owners.

Responsibilities

• Design and build end-to-end test infrastructure for Inference Cloud that supports homogeneous and heterogeneous deployments, runs tests, and tears them down.
• Convert user stories into automated end-to-end tests, including handling failure cases like invalid API keys and unavailable endpoints.
• Bring real hardware into CI by testing on GPU and Corsair nodes, fairly scheduling across a shared pool, and managing flaky tests and failure routing.
• Own the release strategy for orchestration platform, Kubernetes tooling, and benchmarking tools, including versioning and go/no-go criteria.
• Lead the move to independently released components, defining breakdowns, cadence, versioning, and upgrade testing.
• Define release gates covering functional, upgrade/compatibility, and performance baselines.
• Collaborate with QE, product, platform, and infra on a shared test strategy with clear acceptance criteria.
• Enable feature engineers to write and own tests for their work.

Skills

Test infra

Release automation

Kubernetes

CI/CD pipelines

Python/pytest

GPU testing

Cross-team collab

AI tooling

Tools

GitHub Actions

GitLab CI

Buildkite

Argo

AKS

Azure DevOps

Job description

d-Matrix is building the deployment and orchestration tech for inference services, spanning on-prem Corsair/GPU clusters and an Azure cloud. As Staff Test & Release Engineer, you own end-to-end testing and the release process, ensuring features are validated on hardware and delivered safely to customers.

You will extend test infra, partner with QE, product, platform and infra teams, and drive a move to independently released components with clear versioning, gates, and rollback plans.