Anurag Dixit
Machine Learning Engineer at Netflix
Los Gatos, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAnurag Dixit is a Machine Learning Engineer with 9 years of experience building and shipping deep learning solutions from experimental research code to automotive-grade production software. He has driven model optimization, quantization and low-precision deployment across NVIDIA platforms and production pipelines, contributing to projects like Torch-TensorRT and improving compiler integration for efficient inference. At Cruise and NVIDIA he designed end-to-end tooling—frontend model transforms with PyTorch FX, backend compiler passes, TensorRT plugins and SIMD CPU kernels—to meet strict performance and safety requirements for autonomous systems. Now at Netflix in Los Gatos, he continues to bridge research and production, with a pragmatic focus on deployability and runtime efficiency. A detail that stands out: his open-source contributions include documentation and platform-specific fixes for the high-profile pytorch/TensorRT repo, signaling attention to reproducibility and cross-architecture builds.
10 years of coding experience
10 years of employment as a software developer
Bachelor’s Degree, Computer Science, Bachelor’s Degree, Computer Science at UIET, Panjab UniversityMaster’s Degree, Computer Science, Master’s Degree, Computer Science at University at Buffalo
Github Skills (5)
tensorrt10
arm10
pytorch10
documentation10
build-system7
Programming languages (5)
Github contributions (5)
pytorch/TensorRT
Jul 2020 - Sep 2022
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Role in this project:
Back-end Developer
Back-end DeveloperContributions:142 reviews, 194 commits, 98 PRs in 2 years 2 months
Contributions summary:Anurag's commits primarily focus on updating and improving the documentation, specifically addressing aarch64 compilation and installation processes for the repository. They also incorporated review comments to enhance the existing documentation, particularly in the installation tutorials. Furthermore, they rebased the branch with the master branch and added some missing files, and addressed a typo.
compilernvidiapytorchtensorrttorchscript
andi4191/DALI
Nov 2018 - Aug 2019
A library containing both highly optimized building blocks and an execution engine for data pre-processing in deep learning applications
Contributions:3 PRs, 51 pushes, 9 branches in 9 months
pytorchdata-pre-processingpre-processingbuilding-blocksdeep-learning
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.