Rich Harang
Principal Security Architect (AI ML) at NVIDIA
Alexandria, Virginia, United States
Summary
👤
Senior🎓
Top SchoolRich Harang is a Principal Security Architect specializing in AI/ML security with 11+ years applying research-grade machine learning to real-world security problems. He has led AI security at NVIDIA—shaping processes that enabled secure release of hundreds of models, driving cross-company training and shortening approval cycles from weeks to days—while contributing to industry efforts like OWASP LLM risks and the OpenSSF model signing initiative. His background spans defensive and adversarial ML research in industry and government (Sophos, Duo/Cisco, U.S. Army Research Lab), combining a PhD in statistics with hands-on vulnerability discovery and threat modeling for LLMs, generative AI, and agentic systems. Known for translating deep technical issues for both engineers and executives, he also mentors teams to build independent AI security capabilities across business units. An unusual strength is pairing statistical rigor from academic research with practical program-building that moves AI security from theory into production across large enterprises.
11 years of coding experience
8 years of employment as a software developer
BS Biochemistry, BS Biochemistry at Worcester Polytechnic InstitutePhD Statistics and Applied Probability, PhD Statistics and Applied Probability at University of California, Santa Barbara
Spanish, Korean, German
Stackoverflow
181reputation
11kreached
1answer
0questions
Github Skills (32)
datasets10
million9
aws9
python8
machine-learning8
pytorch8
data-science7
lifecycle7
apache-spark7
tensorflow7
deep-learning7
ai6
chainer6
matplotlib6
network-analysis6
Programming languages (3)
Github contributions (5)
sophos/SOREL-20M
Jan 2021 - Apr 2021
Sophos-ReversingLabs 20 million sample dataset
Contributions:6 commits, 5 PRs, 8 pushes in 3 months
datasetsophosmillion
rharang/mtcnn-pytorch
Apr 2019 - Jul 2019
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
Contributions:8 pushes in 2 months
multi-taskface-recognitionconvolutionalalignmentconvolutional-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.