Tether seeks a skilled engineer to own the inference backbone for its local AI stack, focusing on a C++ runtime layer that runs models fast and reliably on real user hardware. You will define core abstractions for inference features and ensure performance and maintainability in production.
You will work on the C++ layer powering local AI, porting and enhancing inference engines like llama.cpp to run efficiently on edge devices. Focus is on runtime speed, lean memory, and cross-hardware stability.
📌 Edge AI Inference Engineer (Colombia)
🏢 Aimlroles
📍 Colombia
Postulate a este anuncio
Muestra tus habilidades a la empresa, rellenar el formulario y deja un toque personal en la carta, ayudará el reclutador en la elección del candidato.