NVIDIA is seeking a driven Software Engineer to join their team focused on Gaussian Splatting and Neural reconstruction. The role involves integrating groundbreaking models into NVIDIA's software ecosystem for neural graphics, enhancing robustness and accuracy. The engineer will work on containerized inference execution for 3D Vision Language Models and contribute to open-source projects. This position offers an opportunity to bridge the gap between real-world applications and simulations in the realm of Physical AI.

• Master's of Science in Computer Science or Electrical Engineering with 3 years of experience, or Bachelor's of Science with 5 years of experience.
• Experience in building, validating, and releasing production-grade AI distributed systems and backend services.
• Deep technical expertise in distributed applications using Docker, Kubernetes, and their APIs.
• Hands-on experience with modern inference platforms such as vLLM, SGLang, Torch, TRT, and TRT-LLM.
• Proficiency in Python and C++.

• Design, build, and optimize containerized inference execution for the latest 3D VLMs from NVIDIA.
• Develop benchmarks to validate the models' accuracy and performance.
• Release and maintain the models and their pipelines throughout their lifecycle.
• Contribute VLM-related features to open-source projects like vLLM.
• Collaborate closely with Research and Product teams to influence common roadmaps.

• Employees at NVIDIA are often offered comprehensive, day-one benefits—including medical, dental, and vision coverage with HSA support, life and disability insurance, an Employee Assistance Program, and a 401(k) with auto-enrollment. Many roles also have generous time off and holidays, donation matching (up to $10,000), and a wide menu of extras like FSAs, commuter benefits, legal and identity-theft protection, pet insurance, and wellness discounts. Optional programs can include student-loan and home-purchase support, plus family care resources and expert medical services.