AIML - Sr. Machine Learning Infrastructure Engineer, Evaluation

How do we ensure that Apple's most advanced AI features perform flawlessly for everyone, everywhere? At Apple, the AI/ML Evaluation team answers this question. We are the architects of quality and trust for AI across all Apple products, from Siri to the iPhone camera. We build the systems and methodologies that rigorously test our models against the complexity and diversity of the real world, ensuring they are robust, fair, and deliver a magical experience.

To truly challenge our models, we must go beyond existing data. This is where you come in. We are looking for a staff engineer to lead the creation of a groundbreaking tooling for synthetic data generation. You will architect the systems that create vast, diverse datasets - spanning text, images, video, and audio - to simulate the edge cases and future scenarios our models will encounter. Your work will be the foundation for a new paradigm of AI evaluation at Apple.

Description

As a Staff Engineer on the AI/ML Evaluation team, you will lead the design and implementation of a platform dedicated to generating high-fidelity synthetic data at an unprecedented scale. You will be responsible for the end-to-end infrastructure that powers a new generation of generative models, enabling us to create realistic and challenging text, image, audio, and video content. This platform is critical to our mission of ensuring Apple's AI is the most reliable and trustworthy in the world. You will be a key technical leader, setting the strategy for how we build, deploy, and leverage generative AI for evaluation.","responsibilities":"Architect a highly scalable, multi-modal platforms for generating synthetic data using the latest generative models.

Design and build robust, high-performance microservices in Golang to serve as the backbone of the data generation platform. Operate and scale distributed compute infrastructure, including large Apple internal job scheduling environments and dedicated GPU clusters.

Develop resilient data pipelines for the curation, processing, and management of massive synthetic datasets.

Define the technical strategy for integrating synthetic data into our core AI evaluation and testing workflows.

Collaborate closely with research scientists and ML engineers to develop novel generative models for evaluation purposes.

Optimize the computational efficiency and scheduling of data generation workloads, with a deep focus on maximizing GPU utilization.

Mentor engineers across the organization on best practices for building and scaling distributed systems for generative AI.

Preferred Qualifications

Direct experience architecting systems for training or running large-scale generative models (e.g., Diffusion Models, GANs, LLMs).

Familiarity with using synthetic data for model testing, validation, robustness checks, or fairness evaluation.

Architectural ownership of a large-scale ML platform or microservice-based system in a production environment.

Strategic leadership in defining technical roadmaps and influencing cross-functional teams in an ambiguous, fast-paced domain.