1 day ago
Base Salary
$155k - $235k/yr
Responsibilities
- Design and build end-to-end test infrastructure that provisions homogeneous and heterogeneous inference deployments, runs tests, and tears them down.
- Translate user stories and acceptance criteria into automated end-to-end tests, including failure scenarios.
- Run tests on GPU and Corsair nodes, schedule fairly on scarce shared hardware, and own flaky-test and failure-routing processes.
- Own release strategy for the orchestration platform, Kubernetes tooling, and benchmarking tools, including versioning, cadence, promotion, rollback, release notes, and go/no-go criteria.
- Lead the transition from platform-wide releases to independently released components and define compatibility and upgrade testing.
- Define release gates covering functional tests, upgrade and compatibility tests, model accuracy evaluations, and performance baselines.
- Partner with QE, product, platform, infrastructure, and architecture teams on shared testing and release strategies.
- Enable feature engineers to write and maintain tests for their own work.
Requirements
- 6+ years of experience in test infrastructure, software engineering in test, release engineering, or a closely related role, including ownership of end-to-end testing or releases for a distributed system.
- Demonstrated experience building test or release automation that improved release reliability or speed.
- Experience operating test and release infrastructure across on-premises clusters and a public cloud, preferably Azure.
- Strong Kubernetes experience, including multi-service workload deployment and debugging, Helm, operators, custom resources, and automated cluster setup and teardown.
- Experience designing CI/CD pipelines with artifact versioning, environment promotion, and rollback.
- Proficiency in Python and pytest or a comparable framework, plus fluency in a second programming language sufficient to read and test qualified code.
- Experience testing shared, limited GPU or accelerator hardware fleets, including scheduling, contention, and hardware faults.
- Ability to make and explain end-to-end testing tradeoffs and build consensus across teams.
- Experience using AI and agentic tools for test writing, failure triage, and log and code search while verifying their output.
- Preferred: experience testing or releasing LLM serving systems such as vLLM, SGLang, or TensorRT-LLM, including accuracy evaluations and performance benchmarks.
- Preferred: familiarity with speculative decoding, disaggregated serving, heterogeneous inference, hardware-in-the-loop testing, operator and controller testing tools, CRD migration testing, customer-managed Kubernetes deployments, canary or progressive rollouts, Rust, or startup environments.
Tech Stack
Categories
About d-Matrix
d-Matrix builds AI inference computing platforms for data centers, combining custom silicon with systems, networking, and software. Its flagship Corsair platform and JetStream fabric focus on low-latency, energy-efficient generative AI inference at scale. Founded in 2019 and headquartered in Santa Clara, California, the privately held company sells hardware with accompanying software to cloud providers and enterprises deploying large AI models.