Staff Test & Release Engineer, Inference Cloud

What you'll do

• Build automated end-to-end test infrastructure and convert user stories into tests, including failure cases.
• Run tests on shared GPU and Corsair hardware, maintain test-signal quality, and route failures to owners.
• Define release strategy, component release practices, and gates for functional, compatibility, accuracy, and performance tests.

What they ask for

• 6+ years in test infrastructure, software engineering in test, release engineering, or a related role, including ownership of end-to-end testing or releases for a distributed system.
• Experience building test or release automation that improved release reliability or speed, and operating infrastructure across on-premises clusters and a public cloud.
• Strong Kubernetes experience and experience designing CI/CD pipelines with promotion and rollback.
• Proficiency in Python and pytest or a comparable framework, fluency in a second programming language, and experience testing shared, limited GPU or accelerator hardware.

Nice to have

• Experience testing or releasing LLM serving systems such as vLLM, SGLang, or TensorRT-LLM, including accuracy evaluations and performance benchmarks.
• Hardware-in-the-loop testing, Rust, or experience with speculative decoding, disaggregated serving, or heterogeneous inference.

Pay

$155K – $235K USD base salary

Tools

Azure, AKS, Azure DevOps, GitHub Actions, Kubernetes, Helm, GitLab CI, Python

AI focus

Build and release test systems for AI inference services, including model accuracy evaluations and performance benchmarks; use AI and agentic tools to write tests, triage failures, and search logs and code.