Deep Learning Compiler Engineer - CUDA Tile & MLIR Focus

NVIDIA; Santa Clara (CA); On-site; USD 152,000 - 242,000; Full time

Job summary

NVIDIA in Santa Clara, CA is hiring software engineers for the CUDA Tile team to design and implement compiler transformations, develop MLIR-based dialects, and optimize tile-based kernels across GPU generations.

You will define public APIs, craft optimization techniques, and contribute to performance engineering and general software engineering work. The role requires 3+ years in compiler optimization, strong C/C++ skills, and the ability to work independently within a dynamic product team.

Qualifications

• Bachelor(s)/Master/PhD in CS/CE or related field (or equivalent experience).
• 3+ years of compiler optimization, performance analysis, IR design.
• Ability to work independently, define goals and lead development.
• Excellent C/C++ programming and software design, debugging and testing.
• Strong interpersonal skills in a dynamic product team.

Responsibilities

• Design and implement compiler transformations for CUDA Tile.
• Develop MLIR-based dialects and lowering passes.
• Optimize performance of tile-based kernels across GPU generations.
• Define public APIs and implement compiler/optimization techniques.
• Perform performance optimization and general software engineering work.

Skills

C/C++ programming

Compiler optimization

Performance analysis

IR design

MLIR

LLVM

XLA

TVM

GPU architecture

OpenCL

Education

Bachelor's/Master's/Ph.D. in CS/CE or related field

Tools

MLIR

LLVM

XLA

TVM

Job description

NVIDIA in Santa Clara, CA is hiring software engineers for the CUDA Tile team to design and implement compiler transformations, develop MLIR-based dialects, and optimize tile-based kernels across GPU generations.

You will define public APIs, craft optimization techniques, and contribute to performance engineering and general software engineering work. The role requires 3+ years in compiler optimization, strong C/C++ skills, and the ability to work independently within a dynamic product team.