Olmo 3

Allyson Ettinger is a senior research scientist at Ai2 working on the OLMo pre-training team. Her public materials focus on natural language understanding, language model behavior, and learning from text and experience.

Amanda Bertsch is a Ph.D. student in the Language Technologies Institute at Carnegie Mellon University. Her research focuses on making language models faster and more memory efficient at test time and improving performance on very long contexts.

Ai2's public team directory lists Bailey Kuehl, and recent public papers credit Kuehl on OLMo Hybrid and scientific-literature work.

Public sources identify David Graham as a member of Ai2's team and a coauthor of OLMo 3.

David Heineman works on the OLMo project at Ai2 and says he previously completed his undergraduate studies at Georgia Tech.

Public sources identify Dirk Groeneveld as an OLMo 3 coauthor; a 2022 USC ISI speaker bio described him as a principal engineer at AI2 and technical lead for the AllenNLP Platform team.

Finbarr Timbers is an AI researcher and investor. His homepage says he works at Ai2 on RL for LLMs and previously worked at Midjourney and DeepMind.

Hamish Ivison's homepage says he is a PhD student in Computer Science and Engineering at the University of Washington working on natural language processing and post-training for language models. Public sources also list him as a coauthor of OLMo 3.

Jacob Morrison's homepage says he is a PhD student at UW and a student researcher on the AllenNLP team at Ai2, where he mainly works on language modeling.

Jakub "Jake" Poznanski identifies himself on his personal site as a Carnegie Mellon computer science graduate and describes leading an OCR toolkit on GitHub.

Kyle Lo's public homepage says he formerly served as a research scientist at the Allen Institute for AI, where he co-led OLMo. It describes current work on large-scale pretraining, data mixing, benchmark validity, and research-supporting data and software artifacts.

Lead research scientist at Ai2 and a founding member of the OLMo team. He works on open language models, language agents, evaluation, and reasoning, and helps build open-model research infrastructure.

Public profiles identify Matt Jordan as an Allen Institute for Artificial Intelligence researcher and a former University of Texas at Austin PhD student advised by Alex Dimakis.

Mayee Chen's public pages describe her as a Stanford computer science Ph.D. student and an AI2 research intern working on data-centric machine learning and natural language processing.

Michael Noukhovitch is a PhD candidate in artificial intelligence at Mila associated with Universite de Montreal. His public homepage lists interests including reinforcement learning, multi-agent systems, natural language processing, and agents with web and computer use.

Nathan Lambert's homepage says he is the post-training lead at Ai2, where he works on open language models and responsible autonomous systems. His public CV lists a PhD in Computer Science from UC Berkeley.

OpenReview lists Evan Pete Walsh as a researcher at the Allen Institute for Artificial Intelligence, and recent public reports credit Pete Walsh on OLMo Hybrid and related open-model work.

Pradeep Dasigi is a research scientist on the AllenNLP team at Ai2. His homepage says he has been actively involved in OLMo and Tulu and currently focuses on post-training language models.

Public sources list Robert Berry on the Ai2 team directory and among the authors of the OLMo 3 technical report.

Saumya Malik is a predoctoral young investigator at the Allen Institute for Artificial Intelligence working on open language modeling, reward models, and instruction following.

Saurabh Shah's public site says he works at humans& and previously worked on post-training the OLMo language model at Ai2.

Scott Geng's homepage identifies him as a University of Washington PhD student and visiting researcher at FAIR; the OLMo 3 technical report lists him as a coauthor.

OpenReview lists Shane Arora as a researcher at the Allen Institute for Artificial Intelligence from 2023 to 2025, an MS student at UT Austin from 2021 to 2024, and an undergraduate student at the University of Sydney from 2016 to 2019. Ai2's public directory and papers pages also list Shane Arora.

Shashank Gupta's public homepage describes him as an applied scientist at Ai2 focused on agentic LLMs, test-time compute, post-training, and reasoning, after earlier work in Microsoft AI.

Canonical link

Allyson Ettinger

Amanda Bertsch

Bailey Kuehl

David Graham

David Heineman

Dirk Groeneveld

Finbarr Timbers

Hamish Ivison

Jacob Morrison

Jake Poznanski

Kyle Lo

Luca Soldaini

Matt Jordan

Mayee Chen

Michael Noukhovitch

Nathan Lambert

Pete Walsh

Pradeep Dasigi

Robert Berry

Saumya Malik

Saurabh Shah

Scott Geng

Shane Arora

Shashank Gupta