AIML - Machine Learning Engineer, Core ML Model Conversion (ODML) Machine Learning Platform & Infrastructure

Summary :

Are you passionate about revolutionizing on-device AI and shaping the future of ML deployment? Join the team behind Core ML, the technology that drives transformative ML features across Apple's ecosystem and beyond.

Our cutting-edge technology leverages the full potential of Apple Silicon to execute neural networks with unprecedented speed and efficiency on Macs, iPhones, Apple Watch, and Vision Pro.

Our team played a pivotal role in the groundbreaking Apple Intelligence features recently unveiled at WWDC, showcasing the cutting-edge capabilities of on-device AI.

We were instrumental in getting the 3B on-device model running on device efficiently. We enable intelligent features in core Apple applications like Camera, Siri, Keyboard, FaceTime, Spatial Computing etc and empower professional-grade third-party applications like Adobe Photoshop, Pixelmator etc to leverage the power of on-device AI.

By harnessing the full potential of Apple's custom-designed CPU, GPU, and Neural Engine, we make it possible for these applications to deliver exceptional AI-powered experiences with unparalleled performance and efficiency.

As a key player in our team, you'll be at the forefront of bridging the gap between the training of state-of-the-art deep learning models and their efficient execution on Apple devices.

Your expertise will be crucial in converting complex computational graphs from frameworks like PyTorch and JAX into optimized, Apple-friendly format that unleashes the full potential of our hardware.

You will work on bringing state of the art models, of varying sizes to run on device with high performance (low latency, memory and power).

We're seeking a highly motivated individual with a deep understanding of ML models and a passion for bringing cutting-edge models from ML research and different domains (vision, image / text generation, audio etc) into real-world applications on device.

If you have a track record of optimizing and deploying models, writing high-quality code, and delivering impactful libraries to a broad user base, we want to hear from you.

In this highly visible role, you'll collaborate with innovative teams across Apple and industry-leading external partners like Adobe, Hugging Face, and Meta.

You will work with them to export and efficiently deploy deep learning models on Apple devices. Your contributions will be instrumental in shaping the future of on-device AI, and you'll play a key role in Apple's open-source initiatives, directly impacting the global AI developer community.

Key Qualifications : Description :

Description :

We are the team that develops Core ML Tools, an open source python library for converting PyTorch and TensorFlow models to Core ML and optimizing models for performance.

If you enjoy playing with the building blocks and architecture of machine learning models, and are strong at understanding the mathematical operations making these models and manipulating the computational graph to optimize for speed / execution, then you are going to have fun in this role! Responsibilities include :

• Performing model conversion from PyTorch, among other libraries, to the Core ML model format
• Running and benchmarking models. Understanding the effect of computational graph representation on the model execution performance on Neural Engine, GPU, CPU.
• Proficient in setting up and running open source ML models (e.g. Hugging Face), understanding ML pipelines and reasoning on which parts should be part of the model, and which ones should be outside of the model as pre-processing and post processing steps
• Adding graph passes for improving performance. Publishing examples of models that are converted in "performant" ways (example : the Apple Stable diffusion open source library)* Collaborate effectively with developers (internal and external).

Be an active member of the open source CoreMLTools community on Github, interacting with developers, addressing GitHub issues etc* Implementing new operations / layers for neural networks

Improving model optimization documentation, writing examples, tutorials and guides Join us in shaping the future of on-device AI and be part of the team that's redefining what's possible with machine learning on Apple devices!

Additional Requirements :