
Senior Machine Learning Applications and Compiler Engineer, LPX
Work on high-performance runtime and compiler components for NVIDIA's LPX inference stack: map large-scale inference workloads to hardware, extend integrations with the software ecosystem, and benchmark/profile to drive performance. Requires MS/PhD or equivalent with 5+ years' relevant experience, strong systems programming (C++ and/or Rust), compiler/runtime experience (IR, optimization passes, codegen), familiarity with LLVM/MLIR, and experience with TensorFlow/PyTorch and ONNX.








