Hussein Mozannar
Senior Researcher at Microsoft
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolHussein Mozannar is a Senior Researcher at Microsoft Research AI Frontiers and a PhD graduate from MIT with nine years of experience at the intersection of human-AI interaction, statistics, and applied machine learning. His work focuses on improving human-AI team performance across domains from healthcare (radiology, pregnancy complications) to code generation and question answering, and he is a member of the HAX team building agentic AI systems. Hussein contributes to high-profile open-source projects such as Microsoft’s autogen, adding backend support for log probabilities in chat completions and fixing multi-agent example subscriptions—demonstrating both research depth and production-grade engineering. He blends rigorous academic training with hands-on systems development, having held research and internship roles at ASAPP, TTIC, and MIT, and brings a knack for turning human-centered research into practical tooling for AI agents.
9 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Social & Engineering Systems and Statistics, Doctor of Philosophy - PhD, Social & Engineering Systems and Statistics at Massachusetts Institute of TechnologyScientific French Baccalaureate, Scientific French Baccalaureate at Lycée Franco-Libanais VerdunBachelor of Engineering (BE), Computer and Communications Engineering, Bachelor of Engineering (BE), Computer and Communications Engineering at American University of Beirut
English, French, Arabic
Github Skills (6)
openai-api10
python10
agentic10
llm10
apidoc9
api9
Programming languages (3)
Github contributions (5)
microsoft/autogen
Oct 2023 - Mar 2025
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
Role in this project:
Back-end Developer
Back-end DeveloperContributions:83 reviews, 44 PRs, 136 pushes in 1 year 5 months
Contributions summary:Hussein contributed to the `autogen` project by implementing support for log probabilities in chat completion features, specifically within the `_openai_client.py` and `_types.py` files. They introduced changes to handle logprobs in both `create` and `create_stream` functions. Furthermore, the user fixed subscription issues in the teamone examples, which involved updating multiple sample files such as `mixture_of_agents.py` and `multi_agent_debate.py`. They also contributed to the magentic one example.
agenticagentic-agiagentsaiautogen
husseinmozannar/multimodal-deep-learning-for-disaster-response
Mar 2018 - Sep 2021
Contributions:30 commits, 28 pushes, 1 branch in 3 years 6 months
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.