Senior GPU Compiler Optimization Engineer for AI/ML

NVIDIA Corporation; Washington; Hybride; USD 184 000 - 288 000; Plein temps

Avantages offerts par ce poste

Equity

Benefits package

Career opportunities

Résumé du poste

NVIDIA Corporation is seeking an experienced Compiler Optimization Engineer for our Compute Compiler Team. You will contribute to the MLIR/LLVM-based pipeline, optimizing GPU-centric code paths to maximize AI, HPC, and graphics workloads.

Join a world-class team pushing the boundaries of CUDA and GPU compilers, collaborating with Open-source communities and distributed hardware groups to deliver robust, scalable performance across NVIDIA GPUs.

Qualifications

• BS/MS/PhD in CS/CE or related field, or equivalent experience.
• 8+ years experience in Compiler Optimizations such as Loop Optimizations, Inter-procedural, Global.
• Excellent hands-on C++ programming skills.
• Understanding of Processor ISA (GPU ISA would be a plus).
• Strong software engineering practices and communication skills.

Responsabilités

• Analyze the performance of application code running on NVIDIA GPUs with the aid of profiling tools.
• Identify opportunities for performance improvements in the MLIR/LLVM based compiler middle end optimizer.
• Identify and Implement novel ideas in the compilation pipeline to enable overall best-in-class performance of AI workloads.
• Design and develop new compiler passes and optimizations to produce best-in-class, robust, supportable compiler and tools.
• Interact with Open-source LLVM community to ensure tighter integration.
• Work with geographically distributed compiler, hardware and application teams to oversee improvements and problem resolutions.
• Be part of a team that is at the center of deep-learning compiler technology spanning architecture design and support through higher level languages.

Connaissances

C++ programming

Compiler optimizations

Loop optimizations

Inter-procedural optimizations

Global optimizations

Parallel programming

GPU ISA knowledge

Formation

Bachelor's/Master's/PhD in CS/CE or related

Outils

MLIR

LLVM

Clang

Open-source collaboration

Description du poste

NVIDIA Corporation is seeking an experienced Compiler Optimization Engineer for our Compute Compiler Team. You will contribute to the MLIR/LLVM-based pipeline, optimizing GPU-centric code paths to maximize AI, HPC, and graphics workloads.

Join a world-class team pushing the boundaries of CUDA and GPU compilers, collaborating with Open-source communities and distributed hardware groups to deliver robust, scalable performance across NVIDIA GPUs.