Lukas T.

AI Engineer with a strong focus on Edge AI Inference and Model Optimization for resource-constrained devices. Specializing in quantization, pruning, and deployment of lightweight models on microcontrollers such as the ESP32. Passionate about pushing the boundaries of on-device intelligence by enabling real-time, low-power AI applications without relying on the cloud. Experienced in model conversion workflows (e.g., TensorFlow Lite, ONNX, TinyML), embedded systems integration, and performance tuning for ultra-low-latency AI. On a mission to make powerful AI run anywhere, even on the tiniest chips.