- Are you passionate about ensuring the highest quality Localized Software and Siri experience for Apple users throughout the world?
- Do you want to collaborate closely with teams across Apple Software Engineering to improve Apple’s Software and Siri experience?
- The Japan Localization Quality team is responsible for designing, implementing and driving both automated and manual test plans to qualify a variety of software products for our international customers.
- We are increasingly applying Agentic AI and large language models (LLMs) to how we test, analyze and scale quality work. We are looking for highly motivated individuals to join our diverse, multicultural team.
- You will make sure that testing for features across many software platforms, languages and locales is done with the highest quality and efficiency under time constraints.
- Perform manual localization testing on software, print documents, help, hardware items, Siri and Apple Intelligence.
- Report issues using internal tools, providing pertinent information and suggestions, and follow each issue through to resolution.
- Analyze international functionality issues.
- Identify areas of improvement in existing tools and processes, and address them with innovative solutions.
- Use LLMs and agentic workflows in day-to-day QA. Examples include test case generation, linguistic issue triage, log and defect analysis, and automating repetitive verification.
- Evaluate the quality of AI-generated and Siri/LLM-driven output in Japanese. This covers naturalness, accuracy, tone, politeness levels (keigo), and cultural appropriateness.
- Design prompts, evaluation criteria and test scenarios that expose weaknesses in language model behavior across locales.
- Work cross-functionally with international software QA centers, engineering teams, translators and project managers to deliver world-class products to international markets.
- Native speaker of Japanese.
- Deep knowledge of linguistics.
- Strong analytical, communication and interpersonal skills.
- Full working proficiency of both written and spoken English.
- Excellent attention to details.
- Excellent team player.
- Self driven, with the flexibility to work on multiple projects with tight deadlines.
- Ability to thrive under pressure and function effectively in a fast-paced environment.
- A person who enjoys breaking the software in order to improve it.
- Experience in software localization.
- Bachelor’s degree in Computer Science or Electronic Engineering, or equivalent experience.
- Working knowledge of how LLMs and generative AI behave, including their limitations such as hallucination, inconsistency and language/locale bias.
- Hands-on, practical experience using LLMs or Agentic AI tools to improve real work. Examples include prompt engineering, building agents or automations, and AI-assisted testing, analysis or content workflows. Please be ready to share concrete examples.
- Experience evaluating or red-teaming LLM output, especially Japanese-language output.
- Scripting or automation skills (e.g., Python, shell) and familiarity with tool-calling, MCP or workflow orchestration.
- Ability to judge when AI output can be trusted and when human linguistic review is essential.
- Working knowledge of localization and internationalization testing (IME input, date/currency formatting, CJK rendering).
- Open to recent university graduates
Job description provided by Apple.
View the original posting