Senior Platform Testing Engineer – AI Inference Infra

Baseten; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Baseten, a platform for AI inference, is seeking a Senior Software Engineer to lead the testing stack on the Platform Team within the Infrastructure organization. You will own end-to-end testing standards, build frameworks for unit, integration, load, and performance tests, and ensure environments can provision realistic dependencies on demand.

This builder role emphasizes resilience testing, fast feedback, and scalable test infrastructure to support customers who rely on low-latency AI services.

Responsibilities

• Own Baseten's testing strategy end to end — define the standards, the tiers, and the tooling that engineering teams build against.
• Build and maintain unit, integration, load and performance testing frameworks
• Design end to end test infrastructure that provisions realistic dependencies on demand — ephem… Kubernetes namespaces, containerized service dependencies, etc.
• Build resilience and chaos testing capabilities: fault injection, network partition and latency simulation, pod and node failure scenarios, dependency degradation, and automated verification that our systems degrade gracefully and recover.
• Attack test suite reliability head-on — flake detection and quarantine, test impact analysis and selective execution, parallelization, and aggressive reduction of end-to-end CI wall time.
• Build observability into the testing layer itself: coverage reporting, test health dashboards, failure triage tooling, and clear signals about which areas of the codebase are under-tested.
• Create project templates and shared libraries so new services start with a complete testing setup on day one.
• Partner directly with product and infrastructure teams — embed where needed, understand their hardest testing problems, and turn one-off solutions into platform capabilities.

Job description

Baseten, a platform for AI inference, is seeking a Senior Software Engineer to lead the testing stack on the Platform Team within the Infrastructure organization. You will own end-to-end testing standards, build frameworks for unit, integration, load, and performance tests, and ensure environments can provision realistic dependencies on demand.

This builder role emphasizes resilience testing, fast feedback, and scalable test infrastructure to support customers who rely on low-latency AI services.