Senior DL Compiler Engineer – CUDA Tile

This is a fully remote position, open to applicants in California, +3 more states.

📋 Description

• Engage in CUDA Tile, a tile-based programming framework designed for NVIDIA GPUs

• Create and execute compiler transformations

• Build MLIR-based dialects and lowering passes

• Enhance tile-based kernel performance across various generations of NVIDIA GPU architectures

• Establish public APIs

• Develop and implement compiler and optimization methodologies

• Conduct performance optimization and general software engineering tasks

• Collaborate with a highly skilled team to influence the deep learning sector

⛳️ Requirements

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

• Over 3 years of pertinent work or research experience in compiler optimization, performance analysis, and IR design

• Capability to work autonomously, establish project objectives and scope, and steer your own development initiatives

• Proficient C/C++ programming and software design abilities, encompassing debugging, performance analysis, and test design

• Strong interpersonal skills with the ability to thrive in a fast-paced, product-focused team environment

• Familiarity with CPU and/or GPU architecture

• Experience in CUDA or OpenCL programming

• Background in MLIR, LLVM, XLA, TVM, as well as deep learning models and algorithms

🏝️ Benefits

• Equity

• Comprehensive benefits package