About this role
Own QA and evaluation infrastructure for multilingual AI agents, including the evaluation agent that gates auto-publishing, annotation tooling, golden datasets, automated evaluation, and feedback loops to improve agents. Build AI-driven localization testing tools to detect localization defects and integrate localization tests into product testing infrastructure.
Skills for this role
Product ManagementAI agent systemsAI agent evaluationEvaluation harnessesPlatform buildingContent platformsTesting platformsSaaS productsLocalizationLocalization testingTranslationLocalization QAAnnotation toolingGolden datasetsAutomated evaluationMetrics dashboardsAnnotation workflow integrationCMSesTesting infrastructureInternal toolingPhraseSmartlingInternationalizationICUCLDRMultilingual (Chinese/European languages)Cross-functional leadershipLinguist collaboration