Jun Ikeda is a software engineer in Tokyo with 12 years' experience building petabyte-scale data pipelines and LLM-powered conversational agents. At LINEヤフー he redesigned extraction and crawl systems to enable independent optimization and higher downstream utility, and now leads development of LangGraph-based shopping agents grounded in automated, persona-driven evaluation. He prioritizes explicit evaluation metrics and optimization units over ad-hoc experimentation, turning ambiguous objectives into continuously improvable systems. His work bridges large-scale distributed infrastructure (Spark/Hadoop) and applied generative AI, with a practical focus on reproducible improvement cycles. Jun holds an MEng from the University of Tokyo and is exploring how real user interaction data can close feedback loops for more robust LLM agent behavior. Despite joking on GitHub about being a "weak coder," his track record shows a disciplined systems thinker who operationalizes evaluation into product impact.
12 years of coding experience
2 years of employment as a software developer
Master of Engineering - MEng, Information Science and Technology, Master of Engineering - MEng, Information Science and Technology at 東京大学
Contributions:47 commits, 16 PRs, 24 pushes in 2 years 2 months
pythonchinese-simplifiedphalcongpanette
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.