Jonathan L. Golob, MD, PhD
Physician-scientist and software engineer
Seattle, WA, USA · [email protected] · golob.org · github.com/jgolob · linkedin.com/in/jonathan-golob
With a view from the bedside, the bench and the codebase, I find what’s missing, build the fix, and leave it working. I lead applied AI/ML for vaccines and infectious disease at GSK, keep a limited clinical practice, and still write the software myself.
Experience
Director, AI/ML — Vaccines & Infectious Disease, GSK · R&D2024 – present
Joined as Lead Engineer, AI/ML (June 2024); promoted to Director (March 2025).
- Built deep-learning models of viral evolution, infection incidence and case-accrual timing, used to guide development and lifecycle decisions for a $1B vaccine program; led their transition into maintained tools.
- Lead GSK's AI/ML and data engineering across all six Fleming Initiative Grand Challenges; GSK scientific co-lead for Antibiotics and Antifungals.
- Built and manage a specialist ML engineering team; form and direct cross-disciplinary teams of 20–30.
- Originated ViroGym, a benchmark for protein language models on viral proteins, and supervised its first author through to a NeurIPS 2026 Spotlight.
Assistant Professor, Internal Medicine / Infectious Diseases, University of Michigan2018 – 2024
- Designed and built MaLiAmPi (senior author; patent pending) and co-led the Microbiome Preterm Birth DREAM Challenge (first author). In 2025 NSF selected the resulting dataset, one of 10 chosen in a competitive interagency process, for the NAIRR Pilot.
- Led a translational research group; protocol co-author and biomarker lead on early-phase trials; site PI for COVID-19 treatment and vaccine trials; global unblinded safety physician.
- Frontline COVID-19 critical care; co-founded the University of Michigan COVID-19 case series; early contributor to the ISARIC dataset; co-author of an early tocilizumab study.
Senior Fellow · Joel Meyers Endowment Scholar, Fred Hutchinson Cancer Center / University of Washington2015 – 2018
Affiliate, Fred Hutchinson Cancer Center, 2018 – 2022.
- Showed that the gut microbiome predicts severe graft-versus-host disease after stem-cell transplant (first author, Clin Infect Dis 2017; Blood Advances 2019), leading to dietary intervention trials (Nature Medicine 2023).
MD–PhD, Medical Scientist Training Program, University of Washington2001 – 2011
- PhD in Pathology on stem-cell epigenetics, with early high-throughput sequencing and a custom analysis pipeline.
Undergraduate Researcher, Johns Hopkins University School of Medicine1997 – 2001
- In research laboratories from my first year: adenoviral and AAV vectors with Paul Kessler, including a collaboration with Osiris Therapeutics on mesenchymal stem cells for cardiac regeneration; then Linzhao Cheng’s laboratory, where I was second author on three papers on early lentiviral vectors for gene transfer into human blood stem cells (Stem Cells 2001; Blood 2002), work at the foundation of today's stem-cell gene therapies.
How I work: two examples
Making microbiome studies comparableMaLiAmPi → harmonized DREAM Challenge dataset → NSF NAIRR Pilot selection
- The problem. Microbiome studies could not be combined. Each used different laboratory and sequencing methods, so a model trained on one study failed on the next.
- What was missing. A stable, shared set of features that did not depend on taxonomy or on how the samples were processed.
- The fix. Designed and built MaLiAmPi, an open-source workflow that turns raw data from technically different studies into one feature set.
- What it enabled. The harmonized, multi-study dataset behind the Microbiome Preterm Birth DREAM Challenge, with models validated on independent data. In 2025 NSF selected that dataset, one of 10 chosen through a competitive process with 12 federal agencies, for integration into the National Artificial Intelligence Research Resource (NAIRR) Pilot. It also supported the Stabl biomarker-discovery method (Nature Biotechnology), and the method is the subject of a pending patent.
Models that inform vaccine development decisionsGSK · 2024 – present
- The problem. Vaccine development and lifecycle decisions depend on how a virus will evolve and when infections will occur.
- What was missing. Predictive models that decision-makers could use, with the uncertainty stated.
- The fix. Built deep-learning models predicting viral evolution, infection incidence and case-accrual timing, and host–immune interactions, and led their transition into maintained tools.
- What it enabled. Used to guide development and lifecycle decisions for a $1B vaccine program; related approaches supported additional programs in the $100M–$500M range.
Independent engineering
- ChoreCode (chorecode.ai): designed and built alone; evaluates AI coding models on maintenance work with hidden tests, checks on the scorer, unsolvable tasks and cost accounting.
- Forty-plus public repositories; four packages on PyPI; one workflow maintained for eight years (github.com/jgolob).
Clinical
- Clinical Assistant Professor, University of Washington: limited active practice in cancer-related and transplant infections.
- Board certified, ABIM: Internal Medicine (2014), Infectious Disease (2016).
Selected publications
78 publications, including preprints and abstracts; more than 4,100 citations (Google Scholar, November 2026).
- Zhou, Golob, Karimi Mamaghan, Bauer, Schwab. ViroGym. NeurIPS 2026 (Spotlight). Originated the project.
- Golob et al. Microbiome Preterm Birth DREAM Challenge. Cell Reports Medicine, 2023. First author.
- Minot … Golob. MaLiAmPi. Cell Reports Methods, 2023. Senior author.
- Riwes, Golob et al. Dietary intervention in stem-cell transplantation. Nature Medicine, 2023.
- Hédou et al. Stabl. Nature Biotechnology, 2024. Co-author.
- Golob et al. Stool microbiota predictive of severe acute GVHD. Clin Infect Dis, 2017. First author.
Skills
- AI and evaluation: Protein and RNA language models, diffusion approaches, benchmark and evaluation design, uncertainty-aware modeling; Python, PyTorch, Nextflow, SQL.
- Biology and clinical medicine: Infectious disease, oncology and transplantation; clinical trial design and safety oversight; multi-omics, organoid models, vector design.
- Leading people and programs: Matrix leadership of 20–30; building specialist ML teams; build–buy–partner decisions; executive advising.
Education and training
- Transplant Infectious Diseases Fellowship, Fred Hutchinson Cancer Center, 2016–2017
- Infectious Diseases Fellowship, University of Washington, 2013–2017
- Internal Medicine Residency, University of Washington, 2011–2013
- MD–PhD, University of Washington, 2001–2011
- Dual BS degrees in Biomedical Engineering and in Computer Science, Johns Hopkins University, 1997–2001
Writing
Science writing for The Stranger, Ars Technica and The Conversation; Delayed Critical, a stage play on nuclear safety and institutional failure (2026).