Software Engineer, Generative AI Engineering (Japanese/English bilingual)

Proven experience designing and building LLM-powered agents and multi-step agentic workflows, especially for code generation or analysis. Demonstrated ability to design prompts that yield reliable, structured JSON or other structured data formats from LLMs. 4+ years of professional software engineering experience, with strong proficiency in Python and hands-on experience coding AI-native tools and applications. Experience working within large-scale enterprise environments and developing for Platform as a Service (PaaS) models.

Spearhead research and development of specialized LLM based agents for each stage of the SDLC, including Requirement Analysis, Design, Code Generation, and Automated Testing. Design, prototype, and refine the core logic for the Agent Orchestrator, defining how context, artifacts, and human approvals flow between agents in the development pipeline. Develop novel prompting strategies and agent tool-chains that produce reliable, structured outputs (e.g., specification documents, test plans, pull requests) for complex software engineering tasks. Partner with platform engineers to define the requirements for the underlying platform, ensuring it supports advanced agentic concepts like human-in-the-loop workflows within an IDE and asynchronous reviews via GitHub. Prototype the next generation of developer experiences, including tight integration of AI agents within VS Code for real-time coding and testing collaboration. Own the core AI quality metrics for each agent, defining benchmarks for "time saved per task" and "rate of accepted changes" to continuously improve their performance.