Principal Machine Learning Engineer

Build on-device AI inference for a browser-native game runtime, helping state-of-the-art multimodal transformer and diffusion models run fast, small, and reliably inside production. Own the end-to-end optimization and integration stack: export, graph transformation, operator fusion, kernel tuning, and runtime scheduling. Lead engineering standards, mentor engineers, and partner across research and platform teams to meet tight latency, memory, and power budgets across mobile NPUs and GPUs and desktop runtimes.