Lucas Liebenwein
Tech Lead at NVIDIA
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolLucas Liebenwein is a tech lead at NVIDIA with nine years of experience building high-performance ML systems, currently co-leading TensorRT-LLM AutoDeploy to compile PyTorch models into inference-optimized graphs. He joined NVIDIA via the OmniML acquisition, where as founding engineer and chief architect he designed Omnimizer, a scalable platform for efficient ML training and deployment. His background includes a PhD from MIT CSAIL focused on efficient deep learning and autonomous driving, and a track record of shipping model optimization tooling (quantization, pruning, distillation) now open-sourced as NVIDIA ModelOptimizer. Lucas blends deep research rigor with product-grade engineering, consistently bridging novel model optimization methods to user-friendly, scalable inference platforms. Based in New York, he brings hands-on compiler and systems expertise informed by real-world robotics and autonomous-vehicle projects—an uncommon combination that speeds ML research into production.
9 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Massachusetts Institute of TechnologyBachelor of Science - BS Mechanical Engineering, Bachelor of Science - BS Mechanical Engineering at ETH Zürich
German, English, Spanish, French, Latin
Github Skills (61)
python10
acceleration10
machine-learning10
numpy10
model-compression10
pruning10
deep-learning10
gpu10
tinyml10
neural-network10
compression10
tensor10
gpu-acceleration10
neural-architecture-search10
pytorch9
Programming languages (6)
Github contributions (5)
lucaslie/torchprune
Feb 2020 - Oct 2021
A research library for pytorch-based neural network pruning, compression, and more.
Contributions:7 releases, 10 commits, 8 pushes in 1 year 8 months
tensor-decompositionneural-architecture-searchsparsificationsparsitypruning
tarquasso/symRepHybDynSys
Dec 2016 - Dec 2016
Contributions:62 pushes, 1 branch in 6 days
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.