About the Role
Arm's Machine Learning Group is seeking highly motivated and creative Software Engineers to join the Cambridge-based ML Content, Algorithms and Tools team! This Machine Learning Engineer role focuses on advancing the field of AI by optimizing and deploying pioneering models, particularly Large Language Models (LLMs) and Generative AI algorithms. This involves deep analysis of neural networks, optimizing software and hardware, developing innovative solutions, and collaborating with teams to build high-performance AI systems.
Responsibilities
- Work with major ML frameworks (PyTorch, TensorFlow, etc.) to port and develop ML networks.
- Optimize and quantize models for efficient execution on Arm platforms.
- Help ensure multiple Arm products are designed to perform effectively for machine learning.
- Deeply understand complex applications and communicate them in their simplest form to contribute to product designs.
- Influence both IP and system architecture.
Required Skills And Experience
- A background in computer science, software engineering or other comparable skills.
- Experience training and debugging neural networks with TensorFlow and PyTorch using Python.
- Understanding, deploying, and optimizing Large Language Models (LLMs) and Generative AI algorithms.
- Experience using software development platforms and continuous integration systems.
- Familiarity with Linux and cloud services.
- Strong attention to detail to ensure use cases are well understood and critical areas for improvement are identified.
Nice To Have Skills And Experience
- Experience of the inner workings of Pytorch, Tensorflow, Executorch and Tensorflow Lite.
- Experience of developing and maintaining CI/testing components to improve automation of model analysis.
- Good knowledge of Python for working with ML frameworks.
- Good knowledge of C++ for working with optimised ML libraries.
- Previous experience of machine learning projects.
- Experience with deployment optimizations on machine learning models.