Staff Test & Release Engineer

Job Summary

Owning the end-to-end testing and release processes, the full-time Staff Test & Release Engineer will design and build test infrastructure for Inference Cloud, ensuring automated tests validate features and releases while working in a hybrid environment.

Key responsibilities

• Design and implement end-to-end test infrastructure for Inference Cloud, managing deployment and testing of inference services
• Develop automated tests from user stories and acceptance criteria, addressing various failure scenarios
• Oversee the release strategy for orchestration and benchmarking tools, including versioning and compatibility testing

Required qualifications

• 6+ years of experience in test infrastructure, release engineering, or related roles with a focus on distributed systems
• Proven track record of building test or release automation that improves reliability or speed
• Strong experience with Kubernetes and deploying multi-service workloads in cloud environments, preferably Azure
• Proficiency in Python and pytest, with the ability to read and test code in a second programming language
• Experience testing on shared hardware, such as GPU or accelerator fleets, and managing scheduling and contention issues