AI People Wiki

Builders & open source

Jeffrey A. Ruffolo

Machine learning team member, Profluent

Jeffrey A. Ruffolo is a member of the machine learning team at Profluent, which builds AI models for protein design. Profluent's team page says that while studying molecular biophysics at Johns Hopkins, Ruffolo developed machine learning models for antibody structure prediction and antibody-specific language models. Ruffolo is a co-author of the Profluent-E1 protein encoder preprint and the ProGen3 scaling preprint.123

At a glance

Current role
Machine learning team member
Company
Profluent
Sector
Company
Work listed
3
Sources cited
5
Profile reviewed

Research

At Johns Hopkins, Ruffolo worked on machine learning for antibodies. In December 2021 Ruffolo was first author, with Jeffrey J. Gray and Jeremias Sulam, of a paper on deciphering antibody affinity maturation with language models and weakly supervised learning.14

At Profluent, Ruffolo co-authored the April 2025 preprint accompanying the ProGen3 protein generation models and the November 2025 preprint introducing E1, a family of retrieval-augmented protein encoders released for research and commercial use.325

Work and contributions

  • Profluent-E1 600M Open weights

    Co-author of the E1 preprint describing Profluent's retrieval-augmented protein encoder family, released in 150M, 300M and 600M parameter sizes.25

  • Profluent-E1 300M Open weights

    Co-author of the E1 preprint describing the retrieval-augmented protein encoder family that includes the 300M-parameter model.2

  • Profluent-E1 150M Open weights

    Co-author of the E1 preprint describing the retrieval-augmented protein encoder family that includes the 150M-parameter model.2

Timeline

  1. Posted a paper on antibody affinity maturation with language models as first author.4
  2. Co-authored the ProGen3 scaling preprint on protein generation models.3
  3. Co-authored the E1 retrieval-augmented protein encoder preprint.2

Where they work

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

5 sources · profile reviewed Oct 22, 2026 · data updated Oct 22, 2026

  1. Profluent — TeamProfluent · Official page · accessed Oct 22, 2026
  2. E1: Retrieval-Augmented Protein Encoder Models (bioRxiv 10.1101/2025.11.12.688125)bioRxiv · Paper · published Nov 13, 2025 · accessed Oct 22, 2026
  3. Scaling unlocks broader generation and deeper functional understanding of proteins (bioRxiv 10.1101/2025.04.15.649055)bioRxiv · Paper · published Apr 16, 2025 · accessed Oct 22, 2026
  4. Deciphering antibody affinity maturation with language models and weakly supervised learning (arXiv 2112.07782)arXiv · Paper · published Dec 14, 2021 · accessed Oct 22, 2026
  5. Introducing Profluent-E1Profluent · Announcement · published Nov 13, 2025 · accessed Oct 22, 2026