Senior GPU Compiler Software Development Engineer

Luxoft; United States; Remote; USD 90,000 - 120,000; Full time

Job summary

A leading company is seeking a software developer to work on GPU support for OpenAI/Triton, a custom deep-learning compiler. The role includes developing new features, testing implementations, and optimizing performance on GPUs. Ideal candidates should have strong programming skills, experience with compiler internals, and basic Python knowledge, contributing to impactful advancements in machine learning.

Qualifications

• Strong C/C++ programming skills required.
• Experience with compiler internals (llvm, gcc).
• Basic Python programming skills and performance analysis experience are essential.

Responsibilities

• Develop new features and optimize the OpenAI/Triton project for GPUs.
• Communicate with developers, customers, and project managers.
• Implement tests and maintain project documentation.

Skills

C/C++ programming skills

Compiler internals

Basic Python programming skills

Performance analysis

Job description

Project description

Working on GPU support for OpenAI/Triton — a language and compiler for writing highly efficient custom Deep-Learning primitives. Work with the open-source community to analyze, develop, test, and deploy performance improvements for neural networks implemented with Triton on GPUs with ROCm.

Responsibilities

• New features development, support and optimization of OpenAI/Triton project for GPUs. Communication with other developers, customers and project managers. Test implementation, project documentation and verification of system with unit/component/functional tests.

SKILLS

Must have

• Strong C/C++ programming skills
• Experience with compiler internals (llvm, gcc or any other)
• Basic Python programming skills
• Experience in performance analysis

Nice to have

• Basic understanding of ML technologies• Experience with GPGPU (General purpose GPU) computing (HIP, CUDA, OpenCL, etc.)• Experience with PyTorch• Experience with LLVM and MLIR compiler infrastructure, analysis or optimizations implementation• Knowledge of ROCm infrastructure• Experience in CMake, make/ninja build system• GEMM performance fundamentals• Experience with Docker