Marius Arvinte
Research Scientist at Intel Labs
Portland, Oregon, United States
Summary
👤
Senior🎓
Top SchoolMarius Arvinte is a research scientist in Portland with eight years of experience building robust compression, estimation, and baseband algorithms for digital communications and medical imaging. He holds a PhD in Electrical and Computer Engineering from UT Austin and has applied his signal-processing expertise across industry research roles at Intel Labs, Nokia Bell Labs, NXP, and Freescale. His work spans practical 5G (massive MIMO / mmWave) R&D, machine-learning-enabled beam management, and reinforcement-learning approaches to combinatorial optimization. Comfortable straddling theory and implementation, he focuses on algorithms that tolerate real-world impairments and scale to hardware-constrained systems. Less obvious: he has repeatedly moved between deep academic research and commercial engineering, giving him a rare fluency in converting novel estimators into deployable communication stack components.
8 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD, Electrical and Computer Engineering, Doctor of Philosophy - PhD, Electrical and Computer Engineering at The University of Texas at AustinColegiul Naţional "Unirea" FocşaniPOLITEHNICA București National University for Science and Technology
English, French, German
Github Skills (23)
language-model10
deepspeed10
generative-model10
pytorch9
python9
wireless9
gpu9
deep-learning9
machine-learning8
testing8
tensor7
neural-network7
numpy7
gpu-acceleration6
autograd6
Programming languages (2)
Github contributions (5)
mariusarvinte/deep-llr-quantization
Mar 2019 - Dec 2019
Contributions:17 commits, 16 pushes in 9 months
utcsilab/score-based-channels
Nov 2021 - Dec 2022
Source code for paper "MIMO Channel Estimation using Score-Based Generative Models", published in IEEE Transactions on Wireless Communications.
Contributions:60 commits, 3 PRs, 74 pushes in 1 year 1 month
generative-modelwirelessdeep-learningphysical-layer
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.