Edge AI Inference Engineer: Llama.cpp&GGML Expert, Winterthur

Framework Ventures in Zurich, Switzerland is seeking a skilled engineer to work on the C++ layer for local AI. This role involves enhancing and porting inference engines like llama.cpp and ONNX to run efficiently on edge devices. Candidates should excel in C++ and have a strong understanding of deep learning and model architectures. You will deploy machine learning models, collaborate with researchers, and integrate AI features into products. Join us to enable fast, private AI without cloud reliance.#J-18808-Ljbffr