Job Description
The Apple Photos application is a comprehensive photo and video management solution that seamlessly integrates across the entire Apple ecosystem, enabling users to capture, organize, edit, and share their visual memories with unprecedented ease and intelligence. Working on the Photos team means contributing to one of Apple's most personal and widely-used applications, combining cutting-edge AI, elegant design, and robust engineering to help billions of users around the world preserve and relive their most important life moments.
This is a high-impact role where you'll work at the intersection of AI modeling, agentic workflows, information retrieval, software engineering, evaluation and metrics, and help us push the boundaries of how AI can transform Apple’s products.
This role blends traditional software QA skills with advanced evaluation methodologies for modern AI models, including LLMs, multimodal systems, and ML-driven product features. As a member of the team, you will work closely with experienced engineers and machine learning experts to qualify and refine features powered by vision, language, and cross-modal intelligence.
You will be responsible for designing rigorous evaluation strategies for both objective and subjective ML behaviors, creating reliable automated testing pipelines, and developing LLM-driven evaluators that complement human judgement. The ideal candidate is self-directed, creative, and comfortable with ambiguity, with strong technical and interpersonal skills. They have hands-on experience testing ML models directly, defining qualitative scoring rubrics, building reproducible evaluation frameworks, and ensuring that AI behavior is safe, consistent, and aligned with product and on-device constraints.
Interested in this role?
Apply now or save it for later. Get alerts for similar jobs at Apple.
