Deep Learning Compiler Engineer: MLIR & CUDA Tile (Equity)

NVIDIA; Austin (TX); On-site; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in Austin, TX is hiring software engineers for the CUDA Tile team. You will design and implement compiler transformations, develop MLIR-based dialects and lowering passes, and optimize tile-based kernels across generations of NVIDIA GPUs.

The role requires a strong background in C/C++, a PhD/masters/BS in CS/CE, and 3+ years in compiler optimization and IR design. You will work independently and with a dynamic, product-focused team.

Qualifications

• Bachelor's, Masters or Ph.D. in Computer Science, Computer Engineering or a related field (or equivalent experience)

Responsibilities

• Design and implement compiler transformations for CUDA Tile and optimize tile-based kernels.
• Develop MLIR-based dialects, lowering passes, and public APIs.
• Collaborate with a high-caliber team on performance and software engineering tasks.

Skills

C/C++ programming

Independent work

Team collaboration

Communication

Education

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

Tools

MLIR

LLVM

XLA

TVM

CUDA/OpenCL

Job description

NVIDIA in Austin, TX is hiring software engineers for the CUDA Tile team. You will design and implement compiler transformations, develop MLIR-based dialects and lowering passes, and optimize tile-based kernels across generations of NVIDIA GPUs.

The role requires a strong background in C/C++, a PhD/masters/BS in CS/CE, and 3+ years in compiler optimization and IR design. You will work independently and with a dynamic, product-focused team.