I'm an audio engineer from Berlin who accidentally became an AI deployment specialist. As the first engineer at ai-coustics, I spent years testing and building inference solutions to run speech enhancement models in real-time across every device imaginable, eventually writing our own inference engine in Rust from scratch. I now lead SDK development, which mostly means figuring out how to make AI models work everywhere while keeping the audio glitches at bay. Former C++ developer, current Rust enthusiast, and lifelong musician.