Amirali Aghazaeh received his B.S. degree in Electrical Engineering from Sharif University of Technology in 2010. He earned his Ph.D. degree in Electrical and Computer Engineering (ECE) from Rice University in 2017. Before joining Georgia Tech in Fall of 2022, he spent three years in the department of Electrical Engineering and Computer Sciences (EECS) at University of California, Berkeley, and two years in the department of Electrical Engineering at Stanford as a Postdoctoral Scholar. Dr. Aghazadeh is the recipient of Berkeley Postdoctoral Association Professional Development award and Hershel M. Rich Invention award for his doctoral thesis. His research connects machine learning, deep learning, and applied mathematics with cutting edge problems in genomics, biology, and sciences.
- Ph.D., Electrical & Computer Engineering, Rice University, 2017
- B.S., Electrical Engineering, Sharif University of Technology, 2010
- Postdoctoral Training, Machine Learning & Signal Processing, Stanford University and University of California, Berkeley, 2017–2022
Aghazadeh's research focuses on machine learning, high-dimensional statistics, signal processing, and artificial intelligence. His work develops principled algorithms for modeling, inference, and optimization in complex data-driven systems, including biomolecular design and engineering. His research bridges mathematical theory with scalable computation to enable reliable prediction, efficient learning, and interpretable modeling across engineering and biological domains.
Aghazadeh's teaching focuses on core Electrical and Computer Engineering courses in the Digital Signal Processing track. At the undergraduate level, he teaches signals and systems and digital signal processing. At the graduate level, he teaches statistical machine learning, generative AI, and geometric deep learning. His courses emphasize mathematical foundations, algorithmic design, and data-driven modeling for applications in modern sensing, communications, and intelligent systems.
- Discriminating Abiotic and Biotic Organics Using ML on Mass Spectrometry Data (2025)
- SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding (2025)
- SHAP Zero for Biological Sequence Models (2025)
- GOLF: Generative AI Framework for Pathogenicity Prediction (2025)
- Efficient Sparse Fourier Transform for Generalized q-ary Functions (2025)