Senior Machine Learning Applications and Compiler Engineer, LPX
Core
Develop algorithms and optimizations for NVIDIA's LPX inference and compiler stack, mapping large-scale neural network workloads onto future NVIDIA platforms.
Role type
Senior IC machine learning applications and compiler engineer
Builds
High-performance runtime and compiler components for end-to-end inference optimization
Domain
AI inference systems, compilers, and spatial processors
Deliverable
production ML models
Required skills
Systems-level programming (C/C++, Rust), compiler/runtime development (IR design, optimization passes, code generation), LLVM/MLIR expertise, deep learning frameworks (TensorFlow, PyTorch, ONNX), parallel/heterogeneous compute architectures, profiling and benchmarking
Preferred skills
Spatial/dataflow architectures (static scheduling, pipeline/tensor parallelism), open-source contributions to ML frameworks/compilers, research publications (PLDI, CGO, ASPLOS, ISCA, MICRO, MLSys, NeurIPS), large-scale AI distributed inference systems
Technologies
LLVM, MLIR, C, C++, Rust, TensorFlow, PyTorch, ONNX
Responsibilities
Build and maintain high-performance runtime and compiler components; define and implement mappings of large-scale inference workloads; extend and integrate with NVIDIA's SW ecosystem; benchmark, profile, and monitor performance metrics; collaborate with hardware architects to codesign features; prototype and evaluate new compilation techniques; publish technical work on novel compilation approaches
Seniority
Senior, hands-on IC
