Roohollah Amiri
Staff Engineer at Qualcomm
San Diego, California, United States
Summary
👤
Senior🎓
Top SchoolRoohollah Amiri is a Staff Engineer and AI researcher with a decade of experience building on-device AI and hardware-aware optimizations, currently advancing on-device inference at Qualcomm from San Diego. He specializes in quantization (including mixed precision and FP8) and toolchain optimization for mobile, automotive ADAS, and large vision and language models, with direct contributions to AIMET. His background spans reinforcement learning for wireless systems, digital twin and EM simulation for 6G, and practical C++/MATLAB signal-processing systems, reflecting a rare mix of deep theory and production engineering. Roohollah holds a PhD in Electrical and Computer Engineering and has published and open-sourced research artifacts (e.g., GeoNS), demonstrating a pattern of turning academic ideas into deployable systems. Not obvious from the title: he has bridged wireless R&D—RF-SLAM, multipath positioning and full-MIMO transformer prediction—with on-device AI efficiency, enabling ML that actually runs in constrained hardware.
10 years of coding experience
12 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Electrical and Computer Engineering, Doctor of Philosophy (Ph.D.) Electrical and Computer Engineering at Boise State UniversityVisiting Researcher, Visiting Researcher at The University of Texas at AustinMaster’s Degree Electrical Electronics and Communications Engineering, Master’s Degree Electrical Electronics and Communications Engineering at Iran University of Science and Technology
English, Persian
Github Skills (7)
allocation9
qos9
pooling9
partitioning8
abstraction8
deep-learning6
machine-learning6
Programming languages (1)
Github contributions (5)
roamiri/pa_intf_RL
Feb 2018 - Apr 2019
Contributions:25 commits, 24 pushes, 1 branch in 1 year 2 months
roamiri/proximity
Jan 2017 - Sep 2019
A Machine Learning Approach for Power Allocation in HetNets Considering QoS
Contributions:77 commits, 14 PRs, 109 pushes in 2 years 8 months
deep-learningapproachhetnetspoolingallocation
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.