SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
d-Matrix is seeking a Staff Test & Release Engineer to own end-to-end testing and release processes for the Inference Cloud platform, which powers d-Matrix's internal model tuning cloud and customer-facing inference endpoints. The Inference Cloud Engineering team builds deployment and orchestration technology that runs on d-Matrix Corsair accelerators, GPUs, on-premises clusters, and Azure infrastructure.
In this role, you will design and build comprehensive test infrastructure that can stand up heterogeneous inference deployments on demand, execute tests, and tear down environments automatically. You will translate user stories and acceptance criteria into automated end-to-end tests covering normal and failure scenarios (invalid API keys, unavailable endpoints, failed nodes). A key challenge is bringing real hardware into CI—managing GPU and Corsair accelerator nodes as a limited shared pool, ensuring test signal quality, and routing failures to the right teams.
You will 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. You will lead the transition from single platform-wide releases to independently released components, defining component breakdown, versioning, compatibility, and upgrade testing. Release gates will cover functional tests, upgrade and compatibility tests, model accuracy evaluations, and performance baselines (time to first token, time per output token, throughput).
You will partner with QE, product, platform, and infrastructure teams to build a shared test strategy and enable feature engineers to write and own tests for their own work. This is a high-leverage role focused on test infrastructure and release engineering—not manual testing, gatekeeping, company-wide CI/CD, or performance engineering.
REQUIREMENTS:
- 6+ years in test infrastructure, software engineering in test, release engineering, or closely related role, including owning end-to-end testing or releases for distributed systems
- 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 public cloud (preferably Azure: AKS, Azure DevOps, GitHub Actions on Azure, Azure networking and identity)
- Strong Kubernetes experience: deploying and debugging multi-service workloads, Helm, operators, custom resources, automated test cluster setup and teardown
- Experience designing CI/CD pipelines (GitLab CI, GitHub Actions, Buildkite, Argo) including artifact versioning, environment promotion, and rollback
- Proficiency in Python and pytest or comparable framework; fluency in a second language sufficient to read and test code (much orchestration layer is Rust)
- Experience testing on shared, limited hardware (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; ability to explain tradeoffs to code owners
- Record of building consensus across teams and turning input into strategy people follow
- Fluency with AI and agentic tools for writing tests, triaging failures, searching logs and code, with discipline to verify output
PREFERRED:
- Experience testing or releasing LLM serving systems (vLLM, SGLang, TensorRT-LLM) including accuracy evals (GSM8K, HumanEval, MMLU) and performance benchmarks as release gates
- Familiarity with speculative decoding, disaggregated serving, or heterogeneous inference
- Hardware-in-the-loop testing experience
- Experience with operator and controller testing tools (envtest, kuttl, chainsaw) and upgrade/CRD version-migration testing
- Experience shipping software into customer-managed on-premises Kubernetes environments
- Experience with canary or progressive rollouts for customer-facing services
- Rust experience
- Startup experience or comfort with shifting priorities
