Luca Soldaini
Former co-lead of Ai2's Olmo open-model project; now a member of the technical staff at Microsoft AI
- Member of the technical staff, Microsoft AI12
Luca Soldaini works on scalable data methods for language models, from pre-training to post-training. From 2022 to early 2026, Soldaini was a lead research scientist at Ai2 and co-led the Olmo project, which released three generations of fully open models in dense, mixture-of-experts, hybrid, and multimodal variants, together with the data, code, recipes, and checkpoints used to build them. Soldaini is first author of the paper introducing Dolma, a three-trillion-token open corpus for language model pretraining research, and is now a member of the technical staff at Microsoft AI.123
Work
OLMo
Co-led the Olmo project at Ai2, which released dense, mixture-of-experts, hybrid, and multimodal open models alongside their data, code, recipes, and checkpoints.1
Dolma
First author of the paper describing Dolma, a three-trillion-token open corpus built for language model pretraining research, released with an open-source data curation toolkit.3
Earlier roles
- Lead research scientist, Ai2 (Allen Institute for AI)1
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.