Andreas Kieslinger

Andreas Kieslinger is a senior development technology engineer for Generative AI and LLMs at NVIDIA. His current focus is to accelerate AI inference in projects like onnxruntime and llama.cpp. Before joining NVIDIA, he worked in research, building distributed ML training systems at BIFOLD and DIMA labs at TU Berlin. He holds MSc and BSc computer science degrees, also from TU Berlin.