Summary
Jinge Wang is a software engineer and AI safety researcher based in Hangzhou with nine years of experience spanning industry and academia. He currently advances frontier AI safety research and content generation at Concordia AI 安远AI, and founded the AI Safety Study Group to nurture a Chinese community of learners and researchers. His work encompasses mechanistic interpretability, AI safety education, and non-human sentience welfare, including an AI Interpretability Fellowship and the Futurekind program at Electric Sheep. He also leads open knowledge exchange through Gixia, an open research community for rating papers and sharing insights. Previously at Microsoft, he contributed to Bing Maps relevance, and his robotics localization background informs his practical approach to applying LLMs safely in real-world systems.
10 years of coding experience