This role involves leading research and application of safety methods for foundation models at Apple. The team focuses on ensuring that large language models are safe, fair, and robust, with particular attention to agentic safety and multimodal safety across audio and vision. The researcher will collaborate with ML engineers and product teams to develop and implement safety solutions. A strong background in applied machine learning and a commitment to safety and responsibility in foundation models are essential.

• A strong ML background with hands-on experience training models.
• Strong coding skills, including the ability to work with messy, real-world codebases.
• Experience with LLMs and post-training methods, including safety alignment.
• A BS, MS, or PhD in Computer Science, Machine Learning, or a related field, or equivalent experience.
• Strong collaboration and communication skills.

• Define and deliver safety methods for foundation models, emphasizing agentic safety and multimodal safety.
• Research the safety and security risks of agentic systems and build the necessary data and evaluations.
• Help define and safeguard the model's character and persona for consistent and safe behavior.
• Build ways to train and evaluate foundation models with safety in mind for audio and vision modalities.
• Work with engineers and researchers across teams to improve Apple products.

• Employees at Apple are often offered comprehensive benefits that support physical and mental well-being—flexible medical plans, confidential counseling, onsite wellness centers at major campuses, and resources for fitness and daily life. Families typically receive fertility support, paid parental leave with gradual return, caregiving leave, and dependent-care guidance, while financial perks commonly include stock grants (with purchase discounts), 401(k) matching, and income-protection coverage. Employees also see robust time off, Apple University learning and tuition reimbursement, donation matching and paid volunteer hours, and deep product and partner discounts.