Mohammad Naseri
Research Scientist at Flower Labs
United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolMohammad Naseri is a research scientist with a decade of experience at the intersection of federated learning, privacy, and distributed systems, currently contributing to Flower Labs in the UK. He completed a PhD in Computer Science at UCL while building privacy-preserving ML tooling and has internship research experience at Microsoft, Telefonica and Inria. On GitHub he meaningfully advanced differential privacy in the widely used Flower federated AI framework—adding central DP methods, client/server clipping, improved docs, logging, and demoed DP combined with secure aggregation. His background blends rigorous academic research with hands-on engineering across industry and institutes, enabling him to turn theoretical privacy mechanisms into usable open-source features. Colleagues know him for pragmatic implementations that bridge research prototypes and production-ready federated learning components.
10 years of coding experience
8 years of employment as a software developer
Bachelor of Applied Science (B.A.Sc.) Computer Software Engineering, Bachelor of Applied Science (B.A.Sc.) Computer Software Engineering at Iran University of Science and TechnologyMaster's degree Computer Science, Master's degree Computer Science at Universität des SaarlandesUniversity College London
English, Persian, German
Github Skills (11)
machine-learning10
differential-privacy10
federated-learning10
python10
ai10
web-framework9
application-framework9
app-framework9
pytorch8
tensorflow8
deep-learning7
Programming languages (5)
Github contributions (5)
adap/flower
Dec 2023 - Mar 2025
Flower: A Friendly Federated AI Framework
Role in this project:
ML Engineer
ML EngineerContributions:56 reviews, 67 PRs, 479 pushes in 1 year 3 months
Contributions summary:Mohammad primarily contributed to the development of differential privacy (DP) features within the federated AI framework. Their work involved improving documentation for DP-related components, deprecating legacy DP wrappers, and introducing new central DP methods with both server-side and client-side clipping. They also added logging for DP operations. Furthermore, they implemented and refined the examples to showcase the usage of these DP mechanisms, including a demonstration combining DP with secure aggregation.
federated-analyticsfederated-learning-frameworkmachine-learningkeras-federated-learningflower
mohammadnaseri/mohammadnaseri.github.io
Jan 2020 - Feb 2021
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Contributions:12 pushes in 1 year 1 month
templategithub-pages-templatemmistakesmistakesjekyll
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.