Kaiyuan Zhang
Research Intern at Perplexity
West Lafayette, Indiana, United States
Summary
👤
Senior🎓
Top SchoolKaiyuan Zhang is a researcher and PhD candidate at Purdue who designs security and privacy foundations for real-world agentic AI systems, with eight years of experience bridging academic rigor and product-facing research. He has worked across industry labs—Perplexity, Microsoft Research, AWS Bedrock, and NEC Labs—specializing in threats like prompt injection and alignment/mechanistic interpretability of LLM-driven agents. His publications and policy contributions include responses to NIST/CAISI and practical tooling for safer browsing agents, reflecting both theoretical depth and applied impact. Based in West Lafayette, he combines hands-on experiments with frontier models and an ability to translate findings into industry guidance, making him a go-to researcher for building secure, deployable AI agents.
8 years of coding experience
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at The University of Texas at DallasPhD student, Computer Science, PhD student, Computer Science at Purdue UniversityVisiting Student, Computer Science, Visiting Student, Computer Science at University of Illinois Urbana-Champaign
English, Chinese
Github Skills (29)
graph-representation-learning10
text-analytics9
representation-learning9
text-analysis9
language-modeling8
semantics8
pattern-recognition7
graph-algorithms7
graph7
word-embeddings7
nlp7
structured-data6
machine-learning6
text-classification6
inverted-index6
Programming languages (2)
Github contributions (5)
ICLR23-BANDS/ICLR23-BANDS.github.io
Nov 2022 - Feb 2023
Contributions:16 commits, 22 pushes, 1 branch in 2 months
KaiyuanZh/awesome-graph-representation-learning
Mar 2019 - Oct 2020
A curated list of awesome graph representation learning.
Contributions:7 commits, 1 PR, 6 pushes in 1 year 7 months
representationrepresentation-learningmachine-learninggraph-representation-learninggraph-neural-networks
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.