Senior MLOps Engineer — Edge AI & Hardware Inference

Hudl is seeking a Senior MLOps Engineer for our Hardware Group to scale edge deployment pipelines and create optimised inference engines for devices such as Jetson Orin. You will own the end-to-end edge deployment, from model training artefacts to hardware-specific runtime on thousands of devices globally. You'll collaborate with Data Scientists, Embedded Engineers, and Product Managers to deliver robust, automated pipelines, manage TensorRT/precision trade-offs, and implement canary releases J…