Amirali Aghazadeh

I am an Assistant Professor in the School of Electrical and Computer Engineering at the Georgia Institute of Technology. I serve as Program Faculty for the Ph.D. programs in Machine Learning, Bioinformatics, and Bioengineering, and am affiliated with the IDEaS, IMS, SRI, and Petit Institute (IBB).

Prior to Georgia Tech, I was a postdoctoral researcher at Stanford and UC Berkeley, and earned my Ph.D. at Rice University. My research lies at the intersection of machine learning, information theory, signal processing, and high-dimensional statistics, with the goal of developing rigorous, principled AI methods for scientific discovery.

Current directions are:

• Fundamentals of ML/AI: Generative and diffusion models, principle of fast inference, and limits of learning/inference in discrete spaces
• AI Interpretability: Mechanistic interpretability, attribution, and spectral explainability methods
• Agentic AI: Hypothesis generation, validation, and multi-step reasoning
• AI for Science: Protein design and sequence-function modeling, cryo-EM microscopy, chemistry, and astrobiology

I pronounce my first name Ah-meer-ah-lee and my last name Ah-gah-zah-deh.

• Watch my invited talk at FCCM 2026 on Mechanistic Interpretation of PLMs: Next-Generation Adaptable Computing for Omics (fast forward to 2:27:00).
• Watch my talk on Agentic AI for Hypothesis Generation: ICLR Agentic AI Workshop.
• Watch my talk on Sparsity, Epistasis, and Models of Protein Fitness Functions at Broad Institute: Models, Inference and Algorithm (MIA).