I am a highly motivated Machine Learning Scientist specializing in Neural Network Optimization, particularly for Large Language Models (LLMs). With extensive experience in research and industrial projects, I focus on making AI more efficient through techniques like model sparsification, quantization, and knowledge distillation for deployment on constrained devices.
Who am I?
- 📍 Based in Munich, Germany
- 🎓 MSc in Robotics, Cognition, and Intelligence, TUM
- 🌟 Published research at NeurIPS and AABI on neural network optimization
- 🔧 Skills: LLM Optimization, Bayesian Inference, Model Sparsification, Quantization, Edge AI, Knowledge Distillation
My passion is making complex AI models more efficient and accessible. Whether optimizing LLMs for edge deployment, enhancing inference speed, or reducing model size while maintaining performance, I thrive on creating efficient and robust AI technologies that can run on resource-constrained devices.