Staff Test & Release Engineer (Inference Cloud)

Join d-Matrix, a cutting-edge AI company, as a Staff Test & Release Engineer. In this role, you will be responsible for end-to-end testing and release strategies for our Inference Cloud platform. You will design and build test infrastructure, turn user stories into automated tests, and own the release strategy for our orchestration platform. This is a unique opportunity to work with world-leading engineers and researchers in a fast-paced, innovative environment.

Responsibilities

• Conception et construction d'une infrastructure de test de bout en bout pour le Cloud d'inférence, y compris la mise en place de déploiements d'inférence homogènes et hétérogènes à la demande.
• Transformation des histoires d'utilisateur et des critères d'acceptation en tests automatisés de bout en bout, y compris les cas d'échec tels que les clés API invalides et les points de terminaison non disponibles.
• Responsabilité de la stratégie de publication pour la plateforme d'orchestration, y compris la version, la cadence, la promotion, le retour en arrière, les notes de version et les critères de go/no-go.
• Fluency with AI and agentic tools for writing tests, triaging failures, and searching logs and code, with the discipline to verify their output
• 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
• Record of building consensus across teams and turning input into a strategy people follow
• Experience testing on shared, limited hardware such as GPU or accelerator fleets, accounting for scheduling, contention, and hardware faults
• 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)

Requirements

• Proficiency in Python and pytest or a comparable framework, plus fluency in a second language sufficient to read and test the code under qualification (much of our orchestration layer is Rust)
• 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
• Sound judgment about what to test end to end versus lower in the stack, and the ability to explain tradeoffs to code owners
• Track record of building test or release automation that measurably improved release reliability or speed
• 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

Preferred

• Rust experience
• Startup experience or comfort in environments where priorities shift quickly

Pay

USD 155,000 - 235,000