Key skills
PythonC/C++Computer VisionDeep LearningCUDA3D Computer VisionSoftware EngineeringMathematical FoundationCollaboration SkillsC++CMachine LearningMLOpsSource ControlCI/CDCommunicationCollaboration
About this role
NVIDIA has been transforming computer graphics, PC gaming, accelerated computing, and machine learning for more than 25 years. The role involves building high-fidelity 3D scene representations, collaborating with teams to design and deploy neural reconstruction models, and pushing the boundaries of neural reconstruction technology.
Responsibilities:
- Help building high-fidelity 3D scene representations from sparse or multi-view data
- Collaborate closely with research and development teams to design, train, and deploy advanced neural reconstruction models
- Develop models that capture geometry, appearance, and semantics, to generate 3D scenes and integrate them into production systems and tools
- Help push the boundaries of neural reconstruction technology and tackle intellectually demanding, highly impactful challenges
Requirements:
- Masters degree or equivalent experience; or preferably a PhD degree in Computer Science or a related field
- 5+ years of experience programming skills in Python and C/C++
- Solid mathematical and algorithmic foundation and proven expertise demonstrated through research publications, internships, or significant project experience
- Strong background in computer vision and deep learning
- Excellent software engineering fundamentals (source control, CI/CD, testing/validation, packaging, containerization, release): proven track record developing, testing, and releasing production-grade, complex software
- Ability to develop code in Unix/Linux environments
- Excellent written, visual, and verbal communication skills to present performance challenges, tradeoffs, and architectural alternatives
- Strong collaboration skills to partner with algorithm designers, application developers, and infrastructure and MLOps teams
- Previous experience with 3D computer vision, object reconstruction, scene reconstruction, and computer graphics
- Previous experience with Gaussian Splatting, NeRF, and similar methods
- Proficiency with CUDA
- Ability to convert research into product