Job Description
About the Job Friendli Suite is our SaaS platform that includes microservices, a frontend, multi-cloud infrastructure, enterprise authentication, billing, and organization management. However, what makes this role unique is that our platform delivers AI inference. Validating whether inference works well is a problem that traditional QA methods do not fully solve. A deployment can succeed technically and still produce poor inference. We are looking for a dedicated QA engineer who can own the product's quality, ensuring our product works the way any well-run SaaS platform should, while also developing the approaches needed to validate AI inference quality, model deployments, and integrations that traditional testing alone cannot cover. Key Responsibilities Own quality across FriendliAI's full platform stack: backend microservices, frontend, model deployments, and inference pipelines. Build and maintain automated test suites using pytest, covering unit, integration, and regression testing across backend services. Develop and run load and scalability tests using Locust to validate platform performance under real-world conditions. Own frontend and end-to-end testing with Playwright across the full user-facing product. Design and implement test strategies that account for LLM inference. Work closely with infrastructure and backend engineers to validate model deployment workflows, multi-cloud orchestration, and service integrations. Identify coverage gaps, prioritize test investment, and build tooling and pipelines. Qualifications 3+ years of experience in software quality engineering, with a track record of owning test strategy. Bachelor's or Master's degree in Computer Science, Computer Engineering, or equivalent. Proficiency in Python