Jobs

Scholarships

Courses

Companies

Placements

Community

Home >

Jobs >

Senior GPU Compiler Software Development Engineer

Mexico City, Mexico (Remote)

Senior GPU Compiler Software Development Engineer

1 Month ago • 3-5 Years • Research & Development

About the job

8 skills required for this role

Add these skills to join the top 1% applicants for this job

neural-networks

cpp

python

docker

pytorch

c-make

opencl

cuda

Job Description

This Senior GPU Compiler Software Development Engineer role focuses on enhancing OpenAI/Triton's GPU support. Responsibilities include developing new features, optimizing existing ones, collaborating with developers and customers, implementing tests, and documenting the project. The work involves performance improvements for neural networks using Triton on ROCm-enabled GPUs. Strong C/C++ and GPGPU experience (HIP, CUDA, OpenCL) are essential, along with compiler internals knowledge (LLVM, GCC). Performance analysis skills are highly valued.

Must have:

Strong C/C++ programming skills
GPGPU computing experience (HIP, CUDA, OpenCL)
Compiler internals experience (LLVM, GCC)
Basic Python programming skills
Performance analysis experience

Good to have:

Basic understanding of ML technologies
Experience with PyTorch
LLVM and MLIR experience
ROCm infrastructure knowledge
CMake, make/ninja build system experience
GEMM performance fundamentals
Docker experience

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 GPGPU (General purpose GPU) computing (HIP, CUDA, OpenCL, etc.) or 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 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

Other

Languages

English: B2 Upper Intermediate

Seniority

Senior

View Full Job Description

Upload your resume, increase your shortlisting chances by 80%

About The Company

Luxoft

1110 Active Jobs

Luxoft, a DXC Technology Company (NYSE: DXC), is a digital strategy and software engineering firm providing bespoke technology solutions that drive business change for customers the world over. Acquired by U.S. company DXC Technology in 2019, Luxoft is a global operation in 44 cities and 21 countries with an international, agile workforce of nearly 18,000 people. It combines a unique blend of engineering excellence and deep industry expertise, helping over 425 global clients innovate in the areas of automotive, financial services, travel and hospitality, healthcare, life sciences, media and telecommunications.

DXC Technology is a leading Fortune 500 IT services company which helps global companies run their mission critical systems. Together, DXC and Luxoft offer a differentiated customer-value proposition for digital transformation by combining Luxoft’s front-end digital capabilities with DXC’s expertise in IT modernization and integration. Follow our profile for regular updates and insights into technology and business needs.