Tether is seeking an AI Research Engineer (Kernel & Inference Optimization) to join our AI model team. You will drive innovations in model serving and inference architectures, optimizing deployment across resource-constrained devices and edge platforms. A strong background in GPU kernels and low-level optimizations is essential.
You will design robust inference pipelines, establish performance metrics, and push for high-throughput, low-latency AI systems that scale across real-world applications.