AI Engineer

This role focuses on building next-generation AI-native features centered on RAG, LLMs, and AI Agents. As part of a global team, you will move beyond simple model implementation to deeply integrate AI with UI/UX and complex business workflows, ensuring a high-quality, reliable user experience.

Responsibilities

• End-to-End Ownership: Own the design, development, and operation of AI features, ensuring they are deeply integrated into business workflows to deliver usable AI experiences.
• Technical Leadership: Lead decision-making regarding model selection, inference architecture, RAG design, and agent workflows based on specific use cases, balancing quality with speed.
• Agentic Workflows: Design and implement highly reliable agent-based LLM workflows and build the necessary execution infrastructure by integrating external services and internal APIs.
• Operational Frameworks: Design and implement robust frameworks for evaluation, monitoring, logging, and cost optimization to maintain a trustworthy AI experience.
• Cross-Functional Collaboration: Translate user needs into concrete requirements through stakeholder discussions and collaborate cross-functionally to design optimal solutions.
• Quality Standards: Establish development processes, testing frameworks, and documentation standards while providing code reviews to ensure system scalability and accuracy.

Requirements

Must-Have Skills

• Development Experience: 5+ years of experience in at least one of the following: Python, TypeScript, or Go.
• LLM Expertise: Hands-on experience building applications using LLM APIs (e.g., OpenAI, Anthropic, Google Gemini).
• AI Agents & RAG: Practical experience with AI agent frameworks (e.g., LangChain, CrewAI, Agents SDK) and designing RAG systems, including embedding and vector databases.
• Context Engineering: Experience improving generation quality through prompt optimization and the design of specific evaluation metrics.
• NLP Foundations: Solid foundation in natural language processing (NLP) and experience building data pipelines.
• Language Proficiency: Japanese proficiency equivalent to JLPT N1.

Preferred Skills

• Experience with search infrastructure such as Elasticsearch, OpenSearch, or Vespa.
• System design experience integrating knowledge graphs or structured data with RAG.
• Practical experience designing and operating systems in cloud environments (AWS, Google Cloud, or Azure).
• Expertise in preprocessing and normalizing unstructured text data (e.g., emails, FAQs, and documentation).

Benefits

Schedule

• Work Style: Hybrid work is required (not fully remote); visa support is available.
• Flexibility: Full flex system without core hours.
• Holidays: Weekends, national holidays, and year-end/New Year holidays off.

Professional Growth & Environment

• AI & Developer Tools: Access to a premium suite of tools including ChatGPT Enterprise, Gemini for Google Workspace, Claude Code, Cursor, and GitHub Copilot.
• Equipment: Choice of Mac or Windows laptop (Mac with US keyboard available).
• Development Support: Self-development budget for books, online courses, and certifications, plus language learning support.
• Side Jobs: Permitted with prior approval.

Welfare & Leave

• Special Leave: Sick leave, work-life balance leave, and birthday leave.
• Family Support: Maternity, childcare, and nursing care leave.
• Insurance & Programs: Complete social insurance, influenza vaccination support, and an employee stock ownership program.