Hi, I’m Ali Madani!

I love AI+Biology and am currently working on a new venture in this space. Previously, I led machine learning research initiatives at Salesforce Research utilizing deep learning, language modeling, and computer vision. Most notably, I was the architect of the ProGen moonshot which advances generative modeling for protein design.

I completed my PhD at UC Berkeley and love building startups, with prior experience as a founder and early employee. Feel free to contact me at ali[at]madani.ai.

News:

  • 10/2021: Two papers accepted to NeurIPS 2021!
  • 09/2021: Talks @ Harvard, Novo Nordisk, Zymergen
  • 06/2021: A major milestone! Released our study showing language models can generate diverse and functional artificial proteins across families. Check out the first-ever crystal structure of a protein designed fully by AI!
  • 06/2021: Co-organized a Special Session on Representation Learning in Biology at ISMB/ECCB
  • 01/2021: Our attention interpretability work, BERTology Meets Biology, is accepted to ICLR 2021.
  • 01/2021: Our review paper on computer vision in healthcare is accepted in Nature: Digital Medicine
  • 12/2020: Oral + poster presentations at NeurIPS 2020 workshops MLSB and LMRL for 2 protein modeling papers: ProGen and Profile Prediction.
  • 11/2020: Check out our breast cancer research now published in Nature Communications.
  • 06/2020: Talk @ Pfizer on language modeling for protein engineering.