AI Research Engineer (Kernel & Inference Optimization)

Design and optimize model serving and inference pipelines for edge/mobile AI deployment across resource-constrained devices, from kernel-level optimizations to end-to-end serving architectures. You will implement low-latency, high-throughput inference on diverse hardware, collaborate with cross-functional teams, and advance state-of-the-art techniques for scalable AI on mobile platforms, handling multi-modal data and evaluating performance with real-world metrics.