I’m a research engineer and musician living in the Bay Area.
Previously, I was a Founding Staff Engineer at Predibase and a Senior Software Engineer at Google building generative language models for Google Search and Google Assistant. My published work focused on NLP, LLMs, and evaluation.
Outside of tech, I play the cello, run a sheet music store, and compete in basketball. I founded two music ensembles: String Theory and Columbia Pops.
See my resume.
Technical Work
Publication, Mar 2025
Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks
Justin Zhao, Flor Miriam Plaza-del-Arco, Amanda Cercas Curry. 2024. ArXiv Preprint.
Publication, May 2024
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report
Justin Zhao, Timothy Wang, Wael Abid, Geoffrey Angus, Arnav Garg, Jeffery Kinnison, Alex Sherstinsky, Piero Molino, Travis Addair, Devvret Rishi. 2024. ArXiv Preprint.
Fine-tuning index. Talk.
Blog, March 2024
LoRA Land: Fine-Tuned Open-Source LLMs that Outperform GPT-4
Timothy Wang, Justin Zhao, Will Van Eaton.
Github Repository, Dec 2023
LLM Distillation Playbook
Justin Zhao, Wael Abid. Github (350 stars).
Talk.
Blog, Aug 2023
Getting the Best Zero-Shot Performance on your Tabular Data with LLMs
Timothy Wang, Justin Zhao.
Publication, Dec 2022
CLSE: Corpus of Linguistically Significant Entities
Aleksandr Chuklin*, Justin Zhao*, Mihir Kale. 2022. EMNLP, Natural Language Generation, Evaluation, and Metric (GEM) Workshop.
Dataset.
Blog, Oct 2022
Ludwig 0.6: Gradient Boosted Models, Config Validation, and Pipelined TorchScript
Joppe Geluykens, Daniel Treiman, Connor McCormick, Arnav Garg, Travis Addair, Geoffrey Angus, Julian Bright, Jim Thompson, Daliana Liu, Justin Zhao, Piero Molino.
Blog, June 2022
Ludwig 0.5: Declarative Machine Learning, now on PyTorch
Justin Zhao, Shreya Rajpal, Daniel Treiman, Jim Thompson, Travis Addai, Piero Molino.
ludwig.ai
Podcast with DataTalksClub.
Blog, May 2022
Ludwig AutoML for Text Classification
Anne Holler, Justin Zhao, Avanika Narayan,Travis Addair, Devvret Rishi, Piero Molino.
Blog, Feb 2022
Ludwig AutoML for Deep Learning
Anne Holler, Avanika Narayan, Justin Zhao, Shreya Rajpal, Daniel Treiman, Devvret Rishi, Travis Addair, Piero Molino.
Publication, July 2021
Using Machine Translation to Localize Task Oriented NLG Output
Scott Roy, Cliff Brunk, Kyu-Young Kim, Justin Zhao, Markus Freitag, Mihir Kale, Gagan Bansal, Sidharth Mudgal, Chris Varano. 2021. ArXiv Preprint.
Talk, Oct 2017
Natural Language Generation at Google Research
Justin Zhao, Yufeng Guo. Google Cloud YouTube channel. 100K+ views.