Senior GPU Compiler Software Development Engineer

Luxoft; São Paulo; Presencial; BRL 120.000 - 160.000; Tempo integral

Resumo da oferta

A leading technology consulting firm in São Paulo is seeking a developer to work on GPU support for OpenAI/Triton. This role focuses on developing and optimizing features for neural networks on GPUs. Candidates must have strong C/C++ skills and experience in compiler internals. The position involves testing, documentation, and collaboration with a diverse team to enhance performance. Excellent opportunities for growth in deep learning technologies are provided.

Qualificações

• Strong skills in C/C++ programming required.
• Experience with compiler internals such as llvm or gcc is a must.
• Basic knowledge of Python programming is necessary.
• Experience in performance analysis needed.

Responsabilidades

• Develop and optimize features for OpenAI/Triton project on GPUs.
• Communicate effectively with developers, customers, and project managers.
• Implement tests and document project details.

Conhecimentos

Strong C/C++ programming skills

Experience with compiler internals

Basic Python programming skills

Experience in performance analysis

Ferramentas

Docker

CMake

LLVM

Descrição da oferta de emprego

Overview

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