Osama Yousuf

Graduate Research Assistant osamayousuf@gwu.edu

I am a PhD Candidate in Computer Engineering at the Adaptive Devices and Microsystems (ADAM) Lab from George Washington University, specializing in Machine Learning and Intelligent Systems.

I am a very avid machine learning/AI enthusiast, and deeply enjoy keeping up-to-date with research in the area. I believe the future of AI systems is analog, and architecturally is a mix of modern-day LLMs and classical AI reasoning & search based approaches.

I bring a unique blend of software and hardware engineering expertise from academic as well as industry roles. I can engineer my way around deep learning frameworks (🧠💡 I enjoy experimenting with new ideas; I speak native PyTorch at this point 🐍📊), design & prototype hardware systems (🔧💻 getting better at FPGA-based system design & verification 🛠️⚡), and build AI-first full-stack web applications (🌐🤖).

Throughout my PhD, I have tackled challenges across the hardware-software stack: from characterizing individual devices and crossbar arrays, to creating kernel drivers for analog and mixed-signal systems, and developing software solutions like data-driven device models and deep learning libraries for evaluating and implementing emerging memory technology-based accelerators for deep neural networks of all kinds.

I graduate in Spring 2025 and am actively seeking Research Scientist and Research Engineer opportunities in deep learning and AI. I want to be part of a company with a challenging work environment where I can contribute to advancing AI technologies and grow my expertise.

selected publications

Frontiers

Gradient decomposition methods for training neural networks with non-ideal synaptic devices

Junyun Zhao, Siyuan Huang, Osama Yousuf, Yutong Gao, and 2 more authors

Frontiers in Neuroscience, 2021

DOI Bib

@article{zhao2021gradient,
  title = {Gradient decomposition methods for training neural networks with non-ideal synaptic devices},
  author = {Zhao, Junyun and Huang, Siyuan and Yousuf, Osama and Gao, Yutong and Hoskins, Brian D and Adam, Gina C},
  journal = {Frontiers in Neuroscience},
  volume = {15},
  pages = {749811},
  year = {2021},
  publisher = {Frontiers Media SA},
  doi = {10.3389/fnins.2021.749811},
  url = {https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2021.749811/full},
  dimensions = {true},
}

ICONS

A system for validating resistive neural network prototypes

Brian Hoskins, Wen Ma, Mitchell Fream, Osama Yousuf, and 7 more authors

In International Conference on Neuromorphic Systems 2021, 2021

DOI Bib

@inproceedings{hoskins2021system,
  title = {A system for validating resistive neural network prototypes},
  author = {Hoskins, Brian and Ma, Wen and Fream, Mitchell and Yousuf, Osama and Daniels, Mathew and Goodwill, Jonathan and Madhavan, Advait and Tung, Hoang and Branstad, Mark and Liu, Muqing and others},
  booktitle = {International Conference on Neuromorphic Systems 2021},
  pages = {1--5},
  year = {2021},
  doi = {10.1145/3477145.3477260},
  url = {https://dl.acm.org/doi/abs/10.1145/3477145.3477260},
  dimensions = {true},
}