Remote: Edge AI Inference Engineer (C++/Llama.cpp)

Tether is seeking an engineer to work on the C++ systems layer that powers local AI, enabling private on-device experiences. In this role, you'll ensure the runtime stability and performance of the inference layer, integrating advancements in AI into state-of-the-art products.

You'll collaborate closely with researchers to transition AI models into production. The ideal candidate has a solid background in programming, especially C++, and a degree in Computer Science or a related field, with a penchant for low-level problem-solving.