About the role
ABOUT THE ROLE
Join an early-stage AI infrastructure company as its first QA engineer, owning quality across a GPU fleet management platform. You will test conversational and web interfaces alongside the Kubernetes-based backend, helping ensure infrastructure changes are safe and reliable.
WHAT YOU'LL DO
- Test conversational workflows end to end, including command accuracy and actions performed on live clusters.
- Build evaluations for AI agent behavior, checking response quality, safe actions, and handling of ambiguous or invalid requests.
- Create end-to-end tests for the web interface and verify consistency across product interfaces.
- Write Go integration tests for backend workflows, including installation, upgrades, and failover.
- Provision and remove Kubernetes test clusters to validate controllers, operators, and custom resources across Kubernetes versions.
- Verify alerts reach the appropriate interfaces and channels only when expected.
- Gate releases in CI and convert bugs and incidents into regression tests.
WHAT WE'RE LOOKING FOR
- At least 3 years in QA, SDET, or test automation, with experience building test suites or automation frameworks.
- Strong Go skills, including backend test automation or integration testing, and experience creating end-to-end tests for web UIs.
- Experience with Kubernetes, React, RPC systems such as gRPC, Linux, and CI/CD platforms.
- Familiarity with observability tools such as Prometheus, Alertmanager, or Grafana, and with Kubernetes testing or chaos engineering tools.
- Experience testing LLM-powered or conversational products and building behavioral evaluations is valuable.
- Experience with multicluster tooling, GPU or bare-metal infrastructure, Playwright, or Slack applications is a plus.
COMPENSATION & BENEFITS
Base salary: $180,000 to $200,000 annually. Visa sponsorship is not available.
LOCATION
On-site in San Francisco, United States.