Luca Soldaini
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolLuca Soldaini is an NLP researcher and engineer with 11 years of experience building large-scale question answering and information retrieval systems, currently a Member of the Technical Staff on Microsoft's Superintelligence team. He led data efforts for AI2's OLMo LLM project and previously drove QA and NLU for Alexa at Amazon, bringing research rigor to production ML systems. Luca holds a PhD from Georgetown where his dissertation explored knowledge and language gaps in medical information seeking, a thread that surfaces in his applied work on search and synthesis for Semantic Scholar. As a core organizer at Queer in AI he combines technical leadership with community-building, managing events, scholarships, and sponsor relations. He’s equally at home with open-source LLM research and operational data pipelines, blending deep academic insight with production-focused impact.
11 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at Georgetown UniversityBachelor of Engineering (B.Eng.) Computer Engineering, Bachelor of Engineering (B.Eng.) Computer Engineering at Università degli Studi di Firenze
English, Italian
Stackoverflow
137reputation
2kreached
0answers
1question
Github Skills (177)
transformers10
language-model10
python10
prefix10
datasets10
r-language10
deep-learning10
speech10
gpu10
relation10
fairness-ml10
cython10
medical10
libfdk-aac10
data-processing10
Programming languages (12)
Github contributions (5)
Georgetown-IR-Lab/QuickUMLS
Jun 2016 - Jul 2022
System for Medical Concept Extraction and Linking
Contributions:12 releases, 1 review, 93 commits in 6 years 2 months
nlpextractionnamed-entity-recognitionumlslinking
allenai/smashed
Jul 2022 - Jan 2023
SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batching, and more. Supports datasets from Huggingface, torchdata iterables, or simple lists of dictionaries.
Contributions:38 releases, 18 reviews, 219 commits in 6 months
in-context-learningextractiontorchdatatokenizationtransformations
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.