Netanel Haber
System Software Engineer - LLM Inference at NVIDIA
Tel-Aviv District, Israel
Summary
🤩
Rockstar🎓
Top SchoolNetanel Haber is a system software engineer with six years of experience building LLM inference runtimes and system-level tooling, currently working on vLLM, SGLang and TRTLLM at NVIDIA after Deci.ai’s acquisition. He brings a blend of deep-learning engineering and full-stack/MLOps experience from productionizing ML workloads, plus frontend leadership developing React.js/Node UIs. Earlier work in military metallurgy endowed him with rigorous lab discipline, technical writing and hands-on problem solving that translate into meticulous debugging and performance tuning. Based in Tel Aviv, he combines low-level systems thinking with practical product delivery, often bridging research models and deployable inference stacks.
6 years of coding experience
2 years of employment as a software developer
יב"ע לפיד מודיעין
English, Hebrew
Stackoverflow
458reputation
48kreached
9answers
7questions
Github Skills (117)
python10
gpu10
cpp10
glm10
runtimes10
multimodal10
transformer10
js10
gpt10
tensorrt10
llama10
reinforcement-learning10
amd10
nvidia10
cuda10
Programming languages (8)
Github contributions (5)
netanel-haber/React-SPA-real-estate-listings
Jan 2020 - Feb 2022
real estate dashboard SPA - react (preact & hooks), express, mongoDB, AWS S3 & Lambda
Contributions:12 PRs, 213 pushes, 7 branches in 2 years 1 month
aws-s3mongodbpreactreact
netanel-haber/sglang
Aug 2025 - May 2026
SGLang is a fast serving framework for large language models and vision language models.
Contributions:1 PR, 113 pushes, 16 branches in 8 months
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.