Drive the future of AI as a Senior Machine Learning Applications and Compiler Engineer at NVIDIA, focusing on runtime and compiler optimizations in a hybrid setting.
This role offers the opportunity to craft and maintain high-performance compiler components while defining mappings for large-scale inference workloads. Work alongside experts to benchmark and ensure efficient neural network graph mappings on emerging platforms.
Key Responsibilities:
• Maintain and develop runtime components for efficiency
• Define inference workload integrations with systems
• Benchmark and monitor compiler performance
• Collaborate on architecture feedback and design
• Prototype recent optimization techniques for processors
Requirements:
• Master’s or Ph.D. in relevant technical fields
• Five years of experience in compiler or runtime development
• Proficiency in C/C++ or Rust
• Deep understanding of LLVM, MLIR, and ONNX
• Solid communication skills for cross-team collaboration
Join NVIDIA to push boundaries and influence the next evolution of AI technologies.
#J-18808-Ljbffr