Mayank Rathee
Graduate Student Instructor
Berkeley, California, United States
Summary
👤
Senior🎓
Top SchoolMayank Rathee is a machine learning researcher-engineer specializing in secure and privacy-preserving AI, with 11 years of experience spanning TEEs, MPC, homomorphic encryption, differential privacy, and federated learning. Currently a Machine Learning Intern at Realm Labs and a PhD student at UC Berkeley, he applies mechanistic interpretability and automated reasoning to AI safety while building practical systems for secure inference. His industry internships at Apple, AWS, and Microsoft Research produced deployable systems like CrypTFlow and advances in secure vector search and HE-accelerated ML communication. He has practical open-source experience integrating MPC frameworks (EzPC/ABY) and improving blockchain testing infrastructure (Hyperledger Scorex), reflecting a mix of low-level systems engineering and rigorous validation. At Berkeley he modernized a large undergraduate security course by creating an LLM chatbot and an LLM jailbreaking project, showing a flair for translating research into hands-on teaching tools. Peers describe him as someone who bridges theory and production, delivering provable privacy guarantees while keeping an eye on usability and developer workflows.
11 years of coding experience
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at University of California, Berkeley
Stackoverflow
214reputation
2kreached
0answers
7questions
Github Skills (30)
property-based-testing10
c-language10
testing10
test-framework10
bash10
scala10
script10
blockchain10
cprogramming-language10
dockers9
pool9
docker9
mpo9
openssl8
data-serialization8
Programming languages (7)
Github contributions (5)
mpc-msri/EzPC
Jun 2019 - Aug 2020
Role in this project:
Back-end Developer
Back-end DeveloperContributions:125 commits, 104 pushes, 5 branches in 1 year 2 months
Contributions summary:Mayank primarily contributed to the compilation and execution scripts for examples, focusing on integrating the EzPC framework with the ABY framework. They added and modified scripts to compile, run, and copy generated files for binary and arithmetic operation examples within a Docker environment. Additionally, the user made changes to the Porthos directory, including commenting in a ParallelAES precompute, removing extra files, adding a setup script for Eigen, and adding the license header to each file.
hyperledger-labs/Scorex
Jul 2017 - Oct 2017
Scorex 2.0 Core
Role in this project:QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:13 commits, 3 PRs in 3 months
Contributions summary:Mayank focused on enhancing the testing framework for the `scorex` repository. They added new property tests and generators to validate functionality related to mempool removal, state rollback, and general serialization processes within the blockchain environment. Their contributions primarily involved writing tests and modifying existing components to ensure the system's robustness and reliability. The user demonstrated a strong understanding of testing methodologies within the Scala ecosystem.
scalablockchaincryptocurrencyscorex
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.