Sr. Machine Learning Engineer Apple News

Apple News is seeking an experienced Machine Learning Engineer to build operate and scale the systems that power intelligent features for millions of people every this role you will bring deep expertise in model serving deployment pipelines distributed systems and ML platform infrastructure; enabling the team to ship reliable high-performance ML-powered features across content tagging ranking and personalization. You are someone who thrives at the intersection of software engineering and machine learning and takes pride in building the infrastructure that makes great models matter at scale. At Apple News our ML problems are uniquely hard spanning privacy-preserving personalization on-device considerations and the balance between editorial and algorithmic curation; and we need engineers who are excited to solve them.

As a Machine Learning Engineer on the Apple News team you will build and operate the infrastructure that powers ML-driven product features spanning content tagging ranking clustering and personalization. You will own the systems that host serve and monitor both classical and deep learning models in production ensuring reliability low latency and scalability at Apple scale. You will evaluate trade-offs across tools and technologies make sound architectural decisions and drive ML infrastructure from concept to production. You will collaborate closely with modeling product data science and platform teams to define requirements and deliver features that have measurable impact on user engagement and content quality.

Design build and operate infrastructure to host and serve classical ML models (gradient boosting SVMs) and deep learning models (transformers neural rankers) in production with a strong focus on latency reliability and scalabilitynEvaluate and select the right tools frameworks and infrastructure (Kubernetes Spark Cassandra Solr Spring Boot AWS GCP) for model serving and feature delivery with a strong command of trade-offs across latency cost scalability and reliabilitynCollaborate with model development teams to manage a shared codebase build common data processing libraries and profile/optimize ML workloads.n Build scalable and reusable infrastructure components for data pipelines such as sampling and collecting data for training labeling via human annotations or LLMsnDesign and implement model monitoring observability and alerting systems to ensure production ML systems meet reliability and performance SLAsnAnalyze real-world user interaction data to uncover gaps in training data distributions and derive model success metrics.

MS in Computer Science Machine Learning or a related discipline or equivalent work experience in this domainn5 years of industry experience in machine learning infrastructure or software engineering with a strong ML systems proficiency in Java and Python for production serving systemsnHands-on experience building and shipping production ML infrastructure: model serving deployment pipelines and feature delivery systems using AI/ML workflowsnExperience deploying ML models on cloud platforms (AWS and/or GCP) with a strong understanding of deployment trade-offs across latency cost and scalabilitynExperience with RAG architectures: including retrieval embedding chunking and reranking strategies and deploying agentic AI systems in productionnExperience building data pipelines for A/B test analysis and training dataset creation using tools such as Apache SparknStrong cross-functional communication skills with the ability to translate complex technical concepts for non-technical partners

Familiarity with inference optimization techniques such as quantization batching caching and model distillation to improve serving efficiencynFamiliarity with embedding pipeline infrastructure: building storing refreshing and serving embeddings at scale; experience with vector store design and trade-offs including indexing strategies approximate nearest neighbor search and latency vs. recall considerationsnFamiliarity with content personalization or recommendation systems at consumer scalenTrack record of delivering AI-powered features with measurable impact on user engagement or content quality