Machine Learning Engineer – Recommendations & Personalization (Feature Engineering)

Apple Services Engineering embodies Apple's deep commitment to uniting creativity with technology. Our team powers flagship services—including the App Store, Games, Apple Arcade, Apple TV, Apple Music, Apple Podcasts, and Apple Books—delivering world-class entertainment and experiences to users worldwide across a diverse set of global languages. Through relentless pursuit of excellence and innovation at scale, we consistently meet Apple's high standards for quality and performance. Our engineers design and scale the machine learning systems that make Apple’s services feel uniquely personal. We are now pioneering the next generation of recommendation architectures — blending traditional ranking models with cutting-edge generative and agent-driven intelligence to create adaptive, context-aware, and delightful user experiences. If you are excited about advancing recommendation technology at massive scale — and about exploring how Large Language Models (LLMs), advanced retrieval, and modular ML systems can reshape personalization — we'd love to meet you. As a Machine Learning Engineer specializing in Recommendations & Personalization, you will be a pivotal contributor at the intersection of robust ML infrastructure, innovative recommendation systems, and emerging generative AI technologies. You will design, optimize, and deploy end-to-end recommendation flows — spanning sophisticated feature engineering, model training, real-time inference, and feedback loops. Simultaneously, you will prototype and build next-generation LLM-powered and agentic recommendation concepts that push the boundaries of what's possible. You will partner closely with applied researchers, infrastructure engineers, and data scientists to bring both production-grade ML systems and exploratory generative architectures to life. This is a hands-on, high-impact engineering role that bridges robust system design with forward-looking research and a passion for crafting unparalleled user experiences. Minimum Qualifications: BS, MS or PhD in Computer Science, Machine Learning, or a related technical field. 4 years of hands-on experience developing and deploying production-grade ML systems for personalization, ranking, or recommendation. Strong software engineering skills in Go, Rust, Java, Python, or similar languages, with a proven focus on building scalable, high-performance, and reliable services. Extensive experience with distributed data and ML systems (e.g.,Ray, Spark) and model lifecycle management. Deep understanding of recommendation model architectures, inference optimization techniques, and practical feedback loop implementations. Demonstrated experience designing, implementing, and analyzing A/B tests or advanced online evaluation frameworks. A strong commitment to system reliability, observability, and ultra-low latency in large-scale ML environments. Preferred Qualifications: Strong theoretical understanding and hands-on experience in agent development, LLM fine-tuning, or post-training optimization. Familiarity with or practical experience using modular LLM tooling frameworks such as LangGraph, LangChain. Background in feature store design, embedding systems, or advanced vector retrieval techniques for recommendation pipelines. Expertise in real-time inference, autoscaling strategies, traffic shaping, and cost-performance optimization for ML services. Experience deploying and managing ML workloads on Kubernetes or other containerized environments. Exposure to reinforcement learning, multi-objective ranking, or generative retrieval architectures. Prior work experience in large consumer media or content recommendation domains.