GPU Performance Architect Multimodal Transformers

Luma is seeking a seasoned GPU optimization expert to accelerate multimodal transformer training and inference. You’ll write kernels in CUDA/Triton, optimize PyTorch ops, and push hardware to the limit across distributed multi-node deployments.

You'll own profiling, kernel fusion, and performance monitoring, delivering tangible latency and throughput gains while advancing cutting-edge transformer research.

The GPU Performance Architect for Multimodal Transformers position in the IT & Technology field is open for applications.

Full responsibilities and requirements are described in the listing above.

Learn more about the GPU Performance Architect for Multimodal Transformers role in the description above.

We appreciate your interest in this position.

Join Luma and contribute to our ongoing work.

Take a moment to read everything above and see whether this role is right for you.

This posting is for the GPU Performance Architect for Multimodal Transformers role at Luma, based in United Kingdom.