Summary
Wei Song is a machine learning engineer and research scientist with a Ph.D. in Computer Science and over a decade of software development experience, specializing in cybersecurity and software supply chain protection. He builds production-grade ML systems—ranging from embedding-based function search and vector databases to RL agents for thermal optimization—and has shipped solutions at startups and industry labs. His research has been published in top security venues (CCS, RAID, AsiaCCS) and earned a best paper award for work that influenced binary fuzzing metrics. At Deepbits he combined decompilation, CodeBERT tuning, and vector search to improve cross-architecture function matching, and contributed fuzzing tests that uncovered real vulnerabilities in an OpenSSF-funded SBOM project. More recently he applied LLMs and time-series models to firmware log parsing and edge deployments for real-time anomaly detection and energy savings. Based in San Jose, he pairs rigorous academic research with hands-on engineering to reduce detection lag and harden open-source ecosystems.
8 years of coding experience
13 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Beijing University of Posts and Telecommunications
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Syracuse University
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of California, Riverside
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Huazhong University of Science and Technology