Do you have expertise in CUDA kernel optimization, C++ systems programming, or compiler infrastructure? Join NVIDIA's nvFuser team to build the next-generation fusion compiler that automatically optimizes deep learning models for workloads scaling to thousands of GPUs! We're looking for engineers who excel at parallel programming and systems-level performance work and want to directly impact the future of AI compilation. The Deep Learning Frameworks Team @ NVIDIA is responsible for building nvFuser, an advanced compiler that sits at the intersection of compiler technology and high-performance computing. You'll work closely with the PyTorch Core team and collaborate with Lightning-AI/Thunder, which integrates nvFuser to accelerate PyTorch workloads. We collaborate with hardware architects, framework maintainers, and optimization experts to create compiler infrastructure that advances GPU performance, developing manual optimization techniques into systematic, automated compiler optimizations.