Researcher Profile
Editor reviewedHybrid Transformer–Mamba language models (Jamba)
Language data analyst at AI21 Labs
A useful profile for the data-and-evaluation side of AI work because it points to the people shaping language data quality, annotation, and analysis inside a frontier-model organization.
Organizations
Labs
About This Page
This profile is meant to help you get oriented quickly: why this researcher matters, what to read first, and where to explore next.
Last reviewed
March 18, 2026
The ideas, systems, and research directions that make this person worth knowing.
01
Language data analysis at AI21 Labs
02
Evaluation and annotation workflows for language models
03
Supporting multilingual and product-facing data quality
04
Hybrid Transformer–Mamba language models (Jamba)
05
Jamba: A Hybrid Transformer-Mamba Language Model
06
Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
Canonical papers, project pages, or repositories that anchor this profile.
Additional papers, projects, or repositories that help flesh out the profile.
Additional links that help verify and flesh out this profile.
People worth exploring next because they share topics, labs, or source material with this profile.
A distinctive page in this AI21 cluster because she brings a linguistics and human-evaluation angle to model work, especially around user interaction, multilingual language behavior, and how LLM performance gets tested in practice.
Worth knowing because his work links earlier dense-retrieval research to later MRKL and Jamba systems, which makes his page a good bridge between classic NLP retrieval and newer hybrid LLM stacks.
A worthwhile long-tail researcher page because it makes the data-and-evaluation layer of modern language-model work visible instead of treating frontier systems as if they were only architecture or scaling stories.
A useful systems-facing page because it ties one of the less-public engineers on the Jamba line to the practical work of turning hybrid-model research into shipped model releases.
A better page than the default Jamba stub because it gives one of the quieter AI21 researchers a real place in the company’s hybrid-model program instead of treating him as just another author in a long list.
A strong long-tail researcher page because his public profile explicitly points to factual knowledge and grounding, which are much more useful signals than another generic AI21/Jamba placeholder.