Jacob Munkberg
Principal Research Scientist at NVIDIA
Greater Malmö Metropolitan Area Sweden
Summary
🤩
Rockstar🎓
Top SchoolJacob Munkberg is a Principal Research Scientist at NVIDIA with a decade-plus career bridging academic rigor and industry impact in real-time computer graphics and rendering. He holds a PhD and docent appointment from Lund University and co-founded a graphics startup acquired by Intel, where he later led advanced rendering research before joining NVIDIA. Jacob’s work spans texture compression, culling algorithms, stochastic rasterization, and neural reconstruction—contributing code and CUDA optimizations to high-profile projects like NVlabs/nvdiffrec that extract 3D models, materials, and lighting from images. Known for shipping practical research into production, he combines deep mathematical training with hands-on systems development and a track record of publishing and chairing leading graphics forums. Based in Malmö, he brings an entrepreneurial mindset to long-range graphics solutions and keeps codebases and papers tightly aligned.
6 years of coding experience
18 years of employment as a software developer
Master Applied Mathematics, Master Applied Mathematics at CentraleSupélecDocent (Reader) Computer Science, Docent (Reader) Computer Science at The Faculty of Engineering at Lund UniversityMSc. Engineering Physics, MSc. Engineering Physics at Chalmers University of Technology
Github Skills (6)
cuda10
pytorch10
machine-learning10
computer-vision10
deep-learning10
python9
Programming languages (3)
Github contributions (5)
NVlabs/nvdiffrec
Nov 2021 - Sep 2022
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".
Role in this project:
ML Engineer
ML EngineerContributions:23 commits, 3 PRs, 28 pushes in 10 months
Contributions summary:Jacob primarily contributed to the project by adding, modifying, and updating code related to the core functionality of the deep-learning model. This includes changes to CUDA code, dataset readers, and core model files. The user also updated the documentation and included arXiv links and bibtex entries. The changes suggest a focus on model development, optimization, and keeping the code aligned with the latest versions of the underlying frameworks.
3d-modelspytorchdeep-learning
NVlabs/nvdiffrecmc
Sep 2022 - Oct 2022
Official code for the NeurIPS 2022 paper "Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising".
Contributions:4 commits, 4 pushes, 39 comments in 13 days
denoisingmonte-carlorendering
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.