Xijun Wang is an applied scientist with 11 years of experience specializing in vision-language models, multimodal learning, model architecture design, and model compression for both CNNs and LLMs. Based in Palo Alto, he has driven research and production efforts at Amazon and Google—most recently building AI model search and ranking experiences for Amazon Core Search and developing EgoSoD to teach LLMs when to intervene in social interactions. His work spans efficient video-language alignment (ViLA) and scene-aware complementary item retrieval, producing state-of-the-art results and practical speedups in ECCV- and AAAI-accepted projects. Xijun blends deep academic training (PhD-level research at University of Maryland and ICAS) with hands-on engineering, including security-focused open-source fixes to the widely used pocsuite3 framework. Colleagues value his ability to translate complex multimodal research into scalable systems that improve real-world search and interaction experiences.
11 years of coding experience
6 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Institute of Computing Technology, Chinese Academy of Sciences
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Maryland
pocsuite3 is an open-sourced remote vulnerability testing framework developed by the Knownsec 404 Team.
Role in this project:
Security Engineer
Contributions:15 commits, 5 PRs, 3 issues in 2 years
Contributions summary:Xijun primarily focused on fixing security-related bugs within the pocsuite3 framework. Their commits addressed issues such as proxy configuration, including SOCKS proxy support, and fixed hook request functionality. Furthermore, they introduced new vulnerability types and made adjustments to the API, demonstrating a focus on enhancing the framework's vulnerability testing capabilities and overall security posture.
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.