Senior DL Compiler Engineer: CUDA Tile, MLIR & Equity

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

Job summary

NVIDIA 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 for multi-generation GPU architectures.

You will work on public APIs, optimization techniques, and general software engineering tasks, with a focus on performance and scalable GPU computing in a fast-paced environment.

Qualifications

• Bachelor’s, Master’s or Ph.D. in Computer Science, Computer Engineering or a related field (or equivalent experience)
• 3+ years of relevant work or research experience in compiler optimization, performance analysis and IR design
• Ability to work independently, define project goals and scope, and lead your own development effort
• Excellent C/C++ programming and software design skills, including debugging, performance analysis, and test design
• Strong interpersonal skills are required along with the ability to work in a dynamic product-oriented team

Responsibilities

• Work on CUDA Tile, a new tile-based programming model for GPUs
• Design and implement compiler transformations, develop MLIR-based dialects and lowering passes
• Optimize performance of tile-based kernels across NVIDIA GPU architectures
• Define public APIs and craft compiler/optimization techniques

Skills

C/C++ programming

Compiler optimization

Performance analysis

IR design

Independent work

Team collaboration

Education

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

Tools

MLIR

LLVM

XLA

TVM

Job description

NVIDIA 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 for multi-generation GPU architectures.

You will work on public APIs, optimization techniques, and general software engineering tasks, with a focus on performance and scalable GPU computing in a fast-paced environment.