Deep Learning Compiler Engineer

NVIDIA is seeking a Deep Learning Compiler Engineer for its CUDA Tile team.

The successful candidate will work on CUDA Tile, a new tile-based programming model for NVIDIA GPUs, designing and implementing compiler transformations, developing MLIR-based dialects and lowering passes, and optimizing performance across multiple GPU architectures.

Responsibilities include:

• Designing and implementing compiler transformations
• Developing MLIR-based dialects and lowering passes
• Optimizing performance of tile-based kernels
• Defining public APIs and crafting compiler and optimization techniques
• Leading independent development efforts and working collaboratively in a dynamic team

Requirements:

• Bachelor's, Master's, or Ph.D. in Computer Science, Computer Engineering, or a related field
• 3+ years of experience in compiler optimization, performance analysis, and IR design
• Excellent C/C++ programming and software design skills
• Strong interpersonal skills and ability to work in a team

Preferred qualifications:

• Knowledge of CPU and/or GPU architecture
• Experience with CUDA, OpenCL, MLIR, LLVM, XLA, TVM, and deep learning models and algorithms

NVIDIA offers highly competitive salaries, a comprehensive benefits package, equity, and opportunities to work with top-notch professionals in cutting-edge fields.