Senior AI Inference Engineer - Mobile GPU & Vulkan Kernel

Framework Ventures is seeking an AI Model Engineer in Dubai with deep expertise in kernel development, model optimization, and GPU acceleration. You will be responsible for implementing and optimizing inference kernels for language models, focusing on mobile GPU acceleration using Vulkan. The ideal candidate has proficiency in C++, experience with quantization techniques, and the ability to debug GPU issues across devices. Join us to deliver efficient language model deployments tailored for mobile and edge applications.
#J-18808-Ljbffr