Senior AI Inference Engineer - Vulkan GPU&LoRA Optimizations

Framework Ventures is seeking an experienced AI Model Engineer in Poland. The role focuses on developing and optimizing inference kernels and GPU acceleration methods for language models, particularly for mobile and edge applications. Candidates should have strong proficiency in C++ and GPU programming, along with a solid understanding of quantization techniques and Vulkan framework. This position requires collaboration with cross-functional teams to deliver production-grade language model deployments. #J-18808-Ljbffr