Staff Test & Release Engineer, Inference Cloud

Location: Santa Clara, California, or remote within the United States; hybrid work is available.

Salary: $155,000–$235,000 per year, plus equity and bonus opportunities.

Company

hirify.global develops software and hardware for generative AI inference, including on-premises accelerator infrastructure and cloud-based inference services.

What you will do

• Design and build end-to-end test infrastructure for Inference Cloud deployments across homogeneous and heterogeneous compute environments.
• Convert user stories and acceptance criteria into automated tests covering standard and failure scenarios.
• Run tests on shared GPU and Corsair accelerator fleets while managing scheduling, flaky tests, and failure triage.
• Own release strategy for orchestration, Kubernetes tooling, and benchmarking components, including versioning, promotion, rollback, and go/no-go criteria.
• Define release gates for functional, upgrade, compatibility, model accuracy, and performance testing.
• Partner with QE, product, platform, and infrastructure teams, and enable feature engineers to own tests for their work.

Requirements

• 6+ years of experience in test infrastructure, software engineering in test, release engineering, or a related field.
• Experience owning end-to-end testing or releases for distributed systems and building automation that improves release reliability or speed.
• Experience operating test and release infrastructure across on-premises clusters and a public cloud, preferably Azure.
• Strong Kubernetes experience, including Helm, operators, custom resources, multi-service workloads, and automated cluster setup and teardown.
• Experience with CI/CD pipelines, 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 production code.

Nice to have

• Experience with LLM serving systems such as vLLM, SGLang, or TensorRT-LLM, including accuracy evaluations and performance benchmarks.
• Experience with speculative decoding, disaggregated serving, heterogeneous inference, or hardware-in-the-loop testing.
• Experience testing Kubernetes operators, CRD migrations, upgrade paths, canary releases, or customer-managed on-premises Kubernetes environments.
• Rust experience.
• Startup experience or comfort with rapidly changing priorities.

Culture & Benefits

• Collaborative and inclusive environment focused on respect, humility, direct communication, and execution.
• Medical, dental, and vision coverage.
• 401(k) and rewards tied to individual and company performance.
• Equity and bonus opportunities.