Sr Machine Learning Engineer, Responsible AI

Apple is seeking a Senior Machine Learning Engineer to assess, quantify, and improve the safety and inclusivity of generative AI features. This role focuses on developing pre- and post-ship safety evaluations using human grading and model-based auto-grading for large language models, diffusion models, and multimodal systems. You will research and build auto-grading methodology and infrastructure, working with sensitive content and cross-functional teams to uphold Apple's Responsible AI values.

• Develop metrics for evaluating safety and fairness risks in generative AI features.
• Design datasets and scale data coverage through human and synthetic generation.
• Develop and apply auto-grading technologies for safety evaluations.
• Provide technical direction for team-wide safety auto-grading initiatives.
• Implement data pipelines and collaborate cross-functionally for end-to-end safety evaluations.
• Work with highly-sensitive content, including exposure to offensive material.

• MS or PhD in Computer Science, Machine Learning, Statistics, or related field.
• Experience with generative models for evaluation or product development.
• Strong engineering skills and production-quality Python code.
• Deep experience in foundation model-based AI programming (e.g., DSPy).
• Experience with noisy, crowd-based data labels and human evaluations.