Senior System Software Engineer, Interactive World Models

NVIDIA NVIDIA · Semiconductors · Santa Clara, CA

Senior System Software Engineer to build and improve production-quality systems for world models, simulation, rendering, and real-time inference, focusing on bringing interactive world models from research to real-world use for applications like autonomous vehicles, robotics, medical training, and gaming.

What you'd actually do

  1. Design, build, and improve production-quality systems for world models, simulation, rendering, and real-time inference from prototype through release.
  2. Connect generated worlds, reconstructed scenes, controllable simulation states, and evaluation loops into cohesive end-to-end systems, while improving performance, quality, scalability, and reliability on NVIDIA GPUs.
  3. Collaborate with research, simulation, rendering, robotics, and autonomous-vehicle teams to make technical tradeoffs, integrate capabilities into downstream workflows, and own complex modules or cross-team projects that shape technical direction and roadmaps.

Skills

Required

  • BS, MS, or PhD in Computer Science, Electrical Engineering, Physics, or a related field, or equivalent experience.
  • 8+ years of relevant software engineering experience.
  • Experience in one or more relevant areas: world models, generative video, diffusion or flow-matching models, neural rendering, simulation, robotics, autonomous vehicles, computer vision, or large-scale ML systems.
  • Experience building and optimizing GPU-accelerated software with CUDA and modern ML frameworks such as PyTorch.
  • Demonstrated engineering judgment and a record of turning technically complex prototypes into reliable products through thoughtful tradeoffs, testing, and delivery, along with ownership of complex modules or cross-team projects and clear communication with partners.

Nice to have

  • Hands-on experience building, adapting, evaluating, or deploying world models, video-generation systems, neural simulation, generative 3D, neural rendering, Gaussian splatting, NeRFs, or reconstruction.
  • Experience with real-time or low-latency inference, distributed training or inference, performance profiling, GPU optimization, simulation, synthetic-data generation, robotics, autonomous vehicles, rendering, or digital-twin applications.
  • Contributions to open-source ML, graphics, simulation, or developer platforms; publications, patents, or other demonstrated technical leadership in a relevant area.

What the JD emphasized

  • production-quality systems
  • real-time inference
  • NVIDIA GPUs
  • production
  • real-world use
  • reliable, high-performance systems
  • production-quality systems
  • real-time inference
  • NVIDIA GPUs
  • reliable products
  • complex modules
  • cross-team projects
  • real-time or low-latency inference
  • distributed training or inference
  • performance profiling
  • GPU optimization

Other signals

  • production-quality systems
  • real-world use
  • NVIDIA GPUs
  • developer and customer facing