Roee Hendel

ML Research Engineer

prof_pic.jpg

I was most recently an Algorithm Developer at AI21 Labs.
There I worked on engineering challenges at the boundary of research, particularly in large-scale distributed training of LLMs with reinforcement learning.
Earlier at AI21 Labs, I worked on data, evaluation, and experimentation for fine-tuning (SFT), and on retrieval-augmented generation.

Overall, I have seven years of R&D experience in machine learning across deep learning, natural language processing, computer vision, and reinforcement learning, spanning both academic and industrial research.
I am a graduate of the Talpiot program, through which I completed a B.Sc. in Physics and Computer Science, and I hold an M.Sc. in Computer Science from Tel Aviv University.

I’m excited about tackling the core challenges toward achieving useful, efficient, and safe general intelligence.

selected publications

  1. preview_image.png
    In-Context Learning Creates Task Vectors
    Roee Hendel, Mor Geva, and Amir Globerson
    EMNLP 2023 Findings, 2023
    A model compresses the examples in its prompt into one internal vector that encodes the task and drives its answers.
  2. padding_minimization.png
    Reducing LLM Training Waste with Model-Agnostic Padding Minimization
    Roee Hendel
    AI21 Labs technical blog, 2026
    Padding tokens in training batches waste computation; removing them cut model update time by up to 75%.
  3. structured_rag.png
    Structured RAG for Answering Aggregative Questions
    Omri Koshorek, Niv Granot, Aviv Alloni, and 6 more authors
    arXiv preprint arXiv:2511.08505, 2025
    Some questions span an entire document collection rather than a few passages; this turns the documents into a database and queries it.