Gpu Compiler Software Development Engineer (Gpu, Cuda - Must)

Luxoft Italy; Liguria; In loco; EUR 45.000 - 65.000; Tempo pieno

Descrizione del lavoro

A leading technology company in Italy is seeking a skilled developer to work on GPU support for OpenAI / Triton. This role involves developing new features, optimizing performance, and collaborating with developers and project managers. Candidates should have strong C/C++ programming skills and experience with compiler internals, as well as basic understanding of Python and performance analysis. The position offers a dynamic work environment with opportunities for growth and development.

Servizi

Flexible working hours

Access to Training Center

Continuous learning programs

Employee discounts and perks

Dynamic projects

Knowledge-sharing communities

Team-building events

Friendly company culture

Competenze

• Strong C / C++ programming skills are essential for this role.
• Experience with compiler internals, like llvm or gcc, is a must.
• Basic Python programming skills are also required.
• Candidates should have experience in performance analysis.

Mansioni

• Develop new features for OpenAI / Triton project for GPUs.
• Support and optimize performance for the project.
• Communicate with developers, customers, and project managers.
• Implement tests, document procedures, and verify system functionality.

Conoscenze

Strong C / C++ programming skills

Experience with compiler internals (llvm, gcc or any other)

Basic Python programming skills

Experience in performance analysis

Basic understanding of ML technologies

Experience with GPGPU computing (HIP, CUDA, OpenCL, etc.)

Experience with PyTorch

Experience with LLVM and MLIR

Knowledge of ROCm infrastructure

Experience in CMake, make / ninja build system

GEMM performance fundamentals

Experience with Docker

Descrizione del lavoro

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

Languages

English : B2 Upper Intermediate

Benefits

• Flexible working hours
• Access to Luxoft Training Center (technical & leadership courses)
• Continuous learning & development programs
• Employee discounts and perks
• Dynamic and fast‑paced projects
• Knowledge‑sharing communities
• Brainstorming sessions and idea‑sharing meetings
• Friendly company culture
• Team‑building events & celebrations