Summary
Koki Wataoka is a research engineer based in Tokyo with eight years of experience focused on AI safety and large language model robustness. He develops red-teaming methodologies, safety tuning, and guardrail systems at SB Intuitions while also contributing to AI research initiatives at LY Corporation. Previously he built applied ML solutions at LINE and participated in public-sector AI security work for Japan’s Ministry of Internal Affairs and Communications, reflecting a blend of industry and policy experience. His academic background includes a master's in computer science from Kobe University and a bachelor's in electrical and information engineering from Osaka City University. Colleagues describe him as a pragmatic researcher who bridges theoretical safety concepts and production-ready defenses, often uncovering subtle failure modes overlooked in standard evaluations. Fluent in both research and engineering contexts, he focuses on making LLMs measurably safer in real-world deployments.
8 years of coding experience
3 years of employment as a software developer
学士, 電気情報工学, 学士, 電気情報工学 at 大阪市立大学
Master's degree, Computer Science, Master's degree, Computer Science at Kobe University