GPU Performance Engineer for Multimodal AI

Speedrun Talent Network; France; Remote; EUR 110,000 - 160,000; Full time

Job summary

Luma is seeking an expert to make its multimodal models fast by profiling and optimizing GPU, CPU, and accelerator code for training efficiency and scalable deployment.

You will write kernels in PyTorch, Triton, and CUDA, developing fused kernels and leveraging advanced hardware features for distributed multi-node systems. Strong profiling and transformer optimization expertise are required to excel in this role.

Qualifications

• Expert-level Triton/CUDA programming and GPU optimization.
• Strong PyTorch skills including kernel development.
• Proficiency with profiling tools (NVIDIA Nsight, torch profiler).
• Deep understanding of transformer architectures and attention mechanisms.

Responsibilities

• Profile and optimize GPU/CPU/accelerator code for maximum utilization and minimal latency.
• Write high-performance PyTorch, Triton, and CUDA, dropping to custom operations when needed.
• Develop fused kernels and leverage tensor cores and modern hardware features across platforms.
• Optimize model architectures and implementations for distributed multi-node production deployment.
• Build performance monitoring and analysis tools and automation.
• Research and implement cutting-edge optimization techniques for transformer models.

Skills

Triton/CUDA programming

GPU optimization

PyTorch kernel development

Profiling tools

Tools

NVIDIA Nsight

Torch Profiler

Job description

Luma is seeking an expert to make its multimodal models fast by profiling and optimizing GPU, CPU, and accelerator code for training efficiency and scalable deployment.

You will write kernels in PyTorch, Triton, and CUDA, developing fused kernels and leveraging advanced hardware features for distributed multi-node systems. Strong profiling and transformer optimization expertise are required to excel in this role.