On-device ML Engineer - US Remote

Join Hugging Face on an innovative journey to advance Machine Learning and make it more accessible. We contribute to the development of technology for the betterment of society.

About Hugging Face

We have built the fastest-growing, open-source library of pre-trained models globally. With over 1 Million+ models and 320K+ stars on GitHub, our technology is trusted by more than 15,000 companies, including leading AI organizations such as Google, Elastic, Salesforce, Grammarly, and NASA.

About the Role

As an On-device ML Engineer, you'll explore cutting-edge methods to run models on consumer platforms, focusing on Apple technologies. Your responsibilities will include:

• Optimizing, quantizing, and converting the best models for efficient execution on iPhones and Macs.
• Designing, building, and contributing to open-source software that demonstrates model usage and develops libraries to minimize friction for developers unfamiliar with ML.
• Disseminating methods, facilitating their adoption, and creating tools for the community.

Day-to-day tasks may include:

• Evaluating models based on quality, latency, memory, and storage needs.
• Striving to make SOTA models work efficiently on Apple platforms by converting them to native formats like Core ML or MLX.
• Optimizing model architectures for Apple Silicon platforms, debugging issues, and developing workarounds.
• Writing Swift code to implement or optimize ML tasks, including pre-and post-processing pipelines.
• Producing high-quality technical documentation, such as blog posts, tutorials, guides, social media threads, and demo apps.
• Contributing to open-source projects like coremltools to improve PyTorch operation coverage.
• Creating tools for developers to convert, run, and share models easily.
• Writing or understanding low-level code such as parallel GPU kernels when necessary.

About You

You'll thrive in this position if you:

• Are an Experienced Swift Developer: Have a strong background in Swift development, a practical builder mindset, and a good sense of software and application design.
• Are Passionate About ML: Have a deep understanding of model architectures and a passion for machine learning.
• Have Core ML Proficiency: Experience using Core ML and an understanding of its advantages and limitations.
• Are an Open Source Contributor: Eager to publish and contribute to open-source libraries to help developers adopt ML.
• Are a Versatile Engineer: Can move across different levels of abstraction, from UI to Metal kernels.
• Write Readable Code: Write code that is easy to understand but also optimize the critical path for performance.
• Understand Optimization Techniques: Have a grasp of optimization techniques, from kv-caching in transformers to post-training quantization.
• Have System Understanding: Can identify performance bottlenecks.
• Are Proficient in Various Frameworks: Experience with frameworks such as llama.cpp, MLX, PyTorch, and CoreNet.
• Are a good debugger.
• Can write excellent technical documentation.
• Engage in discussion forums and communities about these topics.

Even if you don't tick every box, we encourage you to apply. We value diversity and are building a team whose skills, experiences, and backgrounds complement one another.

More about Hugging Face

We value diversity, equity, and inclusivity. We are building a workplace where everyone feels respected and supported, regardless of who you are or where you're from. Hugging Face is an equal opportunity employer, and we do not discriminate based on race, ethnicity, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or ability status.

We value development. Work with some of the smartest people in the industry, with a bias for impact and continuous growth. We provide all employees with reimbursement for relevant conferences, training, and education.

We care about