Researcher Profile

Editor reviewed

Mor Zusman

Hybrid Transformer–Mamba language models (Jamba)

Researcher behind AI21's Jamba hybrid-model work

Helpful because it adds contributor-level detail to the original Jamba release, which is exactly the kind of context these long-tail pages need to be useful rather than decorative.

Organizations

AI21 Labs

Labs

AI21

Topics

Systems & Infrastructure

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

Best First Clicks

Jamba: A Hybrid Transformer-Mamba Language Modelpaper AI21 Labsprofile Jambaarticle

Known For

The ideas, systems, and research directions that make this person worth knowing.

Contributions to the original Jamba release

Hybrid model development at AI21 Labs

Open-weight model engineering in the Jamba line

Hybrid Transformer–Mamba language models (Jamba)

Jamba: A Hybrid Transformer-Mamba Language Model

Jamba-1.5: Hybrid Transformer-Mamba Models at Scale

Start Here

Canonical papers, project pages, or repositories that anchor this profile.

Jamba: A Hybrid Transformer-Mamba Language Modelpaper AI21 Labsprofile Jambaarticle Jamba-1.5: Hybrid Transformer-Mamba Models at Scalepaper

Signature Works

Additional papers, projects, or repositories that help flesh out the profile.

AI21 Jamba Large 1.5 model cardarticle

Related Researchers

People worth exploring next because they share topics, labs, or source material with this profile.

Shared canonical source

Dor Muhlgay

Hybrid Transformer–Mamba language models (Jamba)

5 sources

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.

AI21 Systems & Infrastructure

Start HereDor Muhlgay

Shared canonical source

Gal Cohen

Hybrid Transformer–Mamba language models (Jamba)

4 sources

Worth surfacing because he sits inside the original Jamba author group, which helps make the AI21 hybrid-model story legible at the contributor level instead of only at the company level.

AI21 Systems & Infrastructure

Start HereJamba: A Hybrid Transformer-Mamba Language Model

Shared canonical source

Roman Glozman

Hybrid Transformer–Mamba language models (Jamba)

4 sources

Useful because his name sits inside the original Jamba author list, which gives this page a concrete place in the AI21 hybrid-model lineage instead of leaving it as another anonymous seed profile.

AI21 Systems & Infrastructure

Start HereJamba: A Hybrid Transformer-Mamba Language Model

Shared canonical source

Alan Arazi

Hybrid Transformer–Mamba language models (Jamba)

4 sources

A valuable page in this cluster because his public role description is unusually specific: post-training, steerability, and AI-generated evaluation data are exactly the kinds of practical problems strong researcher pages should make discoverable.

AI21 Post-Training & Alignment Evaluation & Benchmarks

Start HereAlan Arazi

Shared canonical source

Amir Bergman

Hybrid Transformer–Mamba language models (Jamba)

3 sources

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.

AI21 Systems & Infrastructure

Start HereAI21 Labs

Shared canonical source

Ben Aviram

Hybrid Transformer–Mamba language models (Jamba)

3 sources

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.

AI21 Systems & Infrastructure

Start HereAI21 Labs