Generative AI Product QA Lead

SoftBank

GenAI

QA

JavaScript

About this role

This role leads quality assurance for customer-facing generative AI products and systems, including products associated with Crystal Intelligence. It sits between product, development, business, and external QA partners, defining what quality means for systems whose outputs can be non-deterministic and may create risks such as misinformation or information leakage.

The work covers QA strategy, quality standards, test policies, release criteria, risk-based test planning, and quality evaluation from requirements through post-release improvement. The lead designs evaluation datasets and criteria for generative AI responses, covering accuracy, factuality, safety, and consistency, while also planning functional, regression, performance, security, API, web-system, and cloud-service testing. Responsibilities include reviewing partner test plans and results, standardizing test automation and quality checks, and leading release decisions based on defects, metrics, and remaining risk.

Applicants must have practical software QA or testing experience and have independently driven quality assurance or testing as a QA lead, test lead, or test manager. Required experience includes designing test strategies from requirements or user use cases, evaluating quality using test results and metrics, handling functional and non-functional testing for web systems, cloud services, or APIs, and coordinating agreement among multiple stakeholders.

This is an AI-generated summary of the employer's original posting — details can be incomplete, out of date or simply wrong. Always confirm everything on the official posting before applying.