Engineering intelligent systems that connect hardware and software.
Embedded AI and ML researcher. I build deep learning that runs on-device — from multimodal biomedical monitoring on an ESP32-S3 to clinical AI systems where every output is traceable to its source.
I work at the intersection of embedded systems, machine learning, and hardware–software co-design — with peer-reviewed publications in edge ML and distributed learning.
I’m a Computer Engineering M.S. graduate from California State University, Northridge (GPA 4.0, ARCS Fellow, May 2026).
My thesis on on-device multimodal biomedical monitoring received the IEEE ICHI 2026 Best Paper Award and the CSUN Distinguished Thesis Award — university-wide, one of four recipients from eighteen theses across all nine colleges — with a patent-pending EdgeGuard adaptive learning framework deployed on ESP32-S3.
I am now CTO at Privii, leading engineering for an AI-powered clinical operations platform, while continuing graduate research at CSUN.
My research sits at the intersection of multimodal wearable sensing, affective computing, and embedded AI — particularly the computational modeling of latent psychological states, including perceived stress, anxiety, emotional arousal, and cognitive load, from continuous physiological signals, using deep learning architectures deployable on resource-constrained hardware.
A multi-task CNN–SE–Transformer running entirely on an ESP32-S3 for real-time ECG arrhythmia, stress, and activity classification — with on-device adaptive learning and motion-aware alerting. No cloud required.
Clinical AI explainer — medication and lab-result explanations quoted verbatim from FDA labelling, plus a medical-student case simulator. Built so clinical facts are never generated by the model.
Trustworthy Embodied Robotics Modeling — a vision-language-action model with language-grounded feedback at every timestep.
Paste a repo URL — get quality scores, bug risks, architecture diagrams, and README suggestions.
Compare GPT, Claude, Gemini, DeepSeek, and Llama — with live runs and model recommendations.
Automated patient caller that phones a clinic voice agent, transcribes the call, and drafts ranked bug reports.
Redundant dual-system flight architecture with seamless failover. Presented at NASA Armstrong Flight Research Center.
Earlier publications appear under former names: Ali, S. and Abdelhakeem, S.K.
In preparation for IEEE Journal of Biomedical and Health Informatics
2026 IEEE 14th International Conference on Healthcare Informatics (ICHI), Minneapolis, MN, USA, 2026, pp. 1037–1046
Submitted to Science of Physical AI Safety Workshop, CoRL 2026
M.S. Thesis, Department of Electrical and Computer Engineering, California State University, Northridge, 2026
2025 59th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2025, pp. 1806–1811
Technologies, vol. 13, no. 3, p. 98, Mar. 2025
In Proc. 6th International Conference on AI & Virtual Reality (AIVR 2022), Springer Nature, pp. 49–60, 2023
California State University, Northridge · May 2026
Thesis Hardware-Accelerated Deep Learning for Multimodal Biomedical Monitoring with On-Device Adaptive Learning — advisor Dr. Shahnam Mirzaei
California State University, Northridge · 2024