Your new company

Subsidiary of a big Japanese motor corporation which is dedicated to developing mobility technologies based on software.

Your new role

• Spearhead the 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 experience, 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.

What you'll need to succeed

• Proven experience designing and building LLM-powered agents and multistep agentic workflows, especially for code generation or analysis.

• Demonstrated the 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 Platform as a Service (PaaS) models.
  
  NICE TO HAVES

• Experience architecting and building developer tools, IDE extensions (e.g., for VS Code), or GitHub Apps.

• Experience with context engineering using technologies such as MCP servers, knowledge bases and tool registries

• Published research or open-source contributions in the field of AI agents, especially for software engineering.

• Experience with Google's Agent-to-Agent (A2A) protocol or similar inter-agent communication standards

• Familiarity with the challenges of software development in the automotive industry.

• Professional fluency in Japanese, both written and spoken.
  
  

What you need to do now

If you're interested in this role, click 'apply now' to forward an up-to-date copy of your CV, or call us now.

If this job isn't quite right for you, but you are looking for a new position, please contact us for a confidential discussion on your career.