Deep Learning Compiler Engineer

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

📋 Description

• Engage in CUDA Tile, a tile-oriented programming framework for NVIDIA GPUs.

• Conceptualize and execute compiler transformations.

• Create MLIR-based dialects and establish lowering passes.

• Enhance the performance of tile-based kernels across various generations of NVIDIA GPU architectures.

• Establish public APIs.

• Develop and apply compiler and optimization strategies.

• Conduct performance optimization as well as general software engineering tasks.

• Collaborate effectively within a product-focused team.

⛳️ 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 intermediate representation design.

• Capability to work independently, establish project objectives and scope, and guide your own development initiatives.

• Proficient in C/C++ programming and software design, including debugging, performance assessment, and test design.

• Strong interpersonal abilities and the capability to thrive in a fast-paced, product-driven team environment.

• Familiarity with CPU and/or GPU architecture.

• Experience with CUDA or OpenCL programming.

• Background in MLIR, LLVM, XLA, TVM, and deep learning models and methodologies.

🏝️ Benefits

• Equity.

• Comprehensive benefits package.