ML Deployment Engineer, Edge AI - Q

AppleHerzliya

Posted 16 days agoStill open, checked 33m ago

About the job

Our team is new, growing, and evolving quickly, and we are hiring across multiple disciplines. We work at the intersection of machine learning, hardware, and software, creating technologies that reshape how people communicate and experience the world around them in everyday life.

We are seeking a highly skilled and motivated ML Deployment Engineer to join our on-device AI team. In this role, you will take state-of-the-art machine learning models and make them run efficiently on Apple silicon — compressing, compiling, and optimizing them to deliver intelligent experiences that run entirely on-device, with the performance, power, and privacy our users expect. On-device intelligence is at the heart of our products. Getting a model from a research checkpoint to a fast, power-efficient feature shipping on millions of devices is a deep engineering challenge that spans model compression, graph compilation, and hardware-aware optimization across the Apple Neural Engine (ANE), GPU, and CPU.

In this role, you will own the model deployment pipeline end to end: taking trained models from research and applied teams, compressing them, converting and compiling them for the target silicon, and tuning them to meet strict latency, memory, and energy budgets. You will be the owner of the entire process - from compilation to runtime on real hardware — profiling where cycles and joules are spent, diagnosing why an operation falls off the accelerator. You will be a key contributor to the entire product development lifecycle, from concept to deployment, ensuring our on-device models are fast, small, and efficient.