Senior ML Infrastructure Engineer - VE Algorithms

Are you passionate about groundbreaking modeling technologies to enrich billions of people? We are the Video Engineering (VE) team at Apple developing cutting-edge video and machine learning algorithms to build the photo and video features that Apple devices are well known for. We are seeking engineers experienced in building infrastructure for training, adapting and deploying large-scale generative models. In this role, you will be working closely with a cross functional team of algorithm design and infrastructure engineers to benchmark, prototype and steer algorithmic choices to best fit our training and deployment infrastructure.

In this role you will be technically hands on, with deep subject matter expertise in ML infrastructure, focusing on distributed and parallelized training of images and videos, and efficient utilization of training hardware.

Responsibilities

• Optimize and profile training pipelines for large-scale visual pre-training across diffusion and auto-regressive architectures.
• Design and implement workload scheduling strategies for distributed training across clusters of thousands of GPUs.
• Profile and optimize across the full compilation stack — from high level graph capture through intermediate representations down to target HW.
• Build and maintain experimentation tooling, dashboards, and scalable CI/CD pipelines tailored to multi-GPU training workflows.

Minimum Qualifications

• BS in Electrical Engineering/Computer Science or a related field, with a focus on machine learning and minimum 3 years industry experience.
• Experience in training and adapting LLMs.
• Advanced fluency in PyTorch.
• Excellent programming skills in Python or C++ and experience contributing software to large projects.
• Experience with distributed training of large models.

Preferred Qualifications

• Strong Machine Learning fundamentals.
• Experience working with large cross-functional and diverse teams.