Are you passionate about deep-learning, computer vision and generative AI? NVIDIA is offering an opportunity for outstanding deep-learning engineers with experience in image reconstruction and neural rendering technologies. Our team is building solutions for the next generation of intelligent machines, based on foundation models. Training these models requires synthetic data collected via digital twins and photo-realistic rendering. This role offers an opportunity to collaborate with world-class experts and push the boundaries of generative AI with applications to digital twins.

What you will be doing:

• Implement and improve deep learning models to generate high-fidelity 3D representations from 2D images using the latest advances in neural rendering, Neural Radiance Fields (NeRF), Gaussian Splatting and photogrammetry.
• Design workarounds to eliminate artifacts that result from real-world adversarial effects, such as non-stationary scenes and lens irregularities.
• Optimize algorithms for efficient training and deployment of these models for the reproduction of very large scale real-life environments.
• Help customers to build digital twin solutions that combine the strengths of neural- and classic- rendering technologies for the generation of training and test data for computer vision foundation models.

• University degree, or equivalent knowledge, in Computer Science, Computer Engineering, Electrical Engineering or Physics/Mathematics degree with Computer Science experience.
• Proficiency in C++, Python, data structures and algorithms and a solid understanding of computer architecture and operating systems.
• 5+ years experience developing algorithms in more than one of the following areas: virtual / augmented reality, photogrammetry, 3D reconstruction, NeRF / 3DGS / neural rendering, visual generative AI, foundation models, vision language models, style transfer.
• Strong understanding of traditional graphics rendering pipeline, such as rasterization and ray-tracing, OpenGL/Vulkan and shading languages.
• Knowledge of gaming engines, such as UE/Unity.

• Experience with multi-modal generative AI.
• Experience handling very large datasets and using large-scale cloud infra for training and deploying AI models.
• Contribution to open-source projects (can be your private project). Please provide link to github repository.
• Extensive experience in contributing to the field of visual generative models, with a strong publication record in top conferences or journals (e.g. NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, SIGGRAPH, etc.)
• Achievements in programming or machine learning competitions, such as Kaggle, HackerRank, TopCoder, etc.