Summary
Jinpeng Miao is a research scientist at Meta with eight years of experience at the intersection of AI security, program analysis, and vulnerability management. He develops evaluation benchmarks and defenses for LLMs and AI agents, builds static analysis tools for native-code vulnerabilities, and improves triage/prioritization of third-party library risks. His work spans practical engineering—multi-language, cross-platform systems and secure-by-default frameworks for mobile—with deep research roots from a PhD focused on secure architectures, edge computing, and intelligent systems. Based in Menlo Park, he blends rigorous academic methods with production-focused tooling, often turning complex security research into usable frameworks and automated analyses. An interesting thread through his career is repeatedly designing systems that elevate security to a first-class engineering constraint, from hardware-aware defenses to AI-agent benchmarks.
8 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Colorado Boulder
Bachelor of Engineering - BE, Electrical, Electronics and Communications Engineering, Bachelor of Engineering - BE, Electrical, Electronics and Communications Engineering at Jilin University