Tether is seeking an AI Research Engineer to advance model serving and inference optimization across diverse architectures, including edge devices. You will design scalable pipelines, push the boundaries of latency, throughput, and memory efficiency, and drive end‑to‑end improvements in real‑world deployments.Adecuado candidates will have a PhD or strong research track, deep knowledge of MSL, and hands‑on experience delivering kernel and inference optimizations for mobile platforms.#J-18808-Ljbffr