SWE - Sr ML Infrastructure Engineer, Siri User Experience Metrics and Data

We are seeking a Senior ML Infrastructure Engineer to design, build, and scale the foundational systems that power our machine learning lifecycle within Siri User Experience Metrics team - from data ingestion to production model deployment. In this role, you will develop robust, scalable, and reproducible ML pipelines and services. This is a high-visibility, high-impact position with the opportunity to influence the direction of products and strategy. The Siri User Experience Metrics team is at the heart of shaping how users interact with Siri every day. We use data, metrics and insights to continuously improve Siri’s User Experience across Apple platforms including iOS, macOS, visionOS, tvOS and watchOS. Our team defines and owns the most critical user facing metrics, builds scalable reporting tools and delivers actionable insights that directly inform product decisions. We collaborate closely with product, platform and feature teams to ensure Siri not only works - but delivers exceptional User Experience. From response time to failure tracking, we make sure Siri feels fast, natural and helpful wherever users need it. As a Senior ML infrastructure Engineer on the Siri User Experience Metrics team, you will have significant influence and responsibility in shaping the architecture and scalability of our end-to-end machine learning infrastructure. You will lead initiatives to streamline model development workflows, ensure reliable deployment of ML models to production, and optimize performance across compute and storage. If this sounds like you, you're someone who is laser-focused on impact - bringing sharp programming skills, strong problem-solving abilities and clear communication to the table, all driven by a passion for building exceptional products. You'll have the opportunity to drive meaningful impact across all Apple platforms by collaborating closely with Engineering, Product, Testing and Quality teams. Your work will directly enhance the Siri experience for billions of users - shaping how people interact with Apple every day.

We’re looking for an engineer to lead the design, development, and scaling of our machine learning infrastructure. This role is ideal for someone who thrives at the intersection of systems engineering and applied machine learning. You’ll be responsible for building robust, scalable, and maintainable infrastructure to support the full ML lifecycle - from data ingestion and feature computation to training, deployment, and monitoring in production. You’ll play a critical role in:

• Designing and maintaining high-throughput, low-latency pipelines for real-time and batch inference.
• Automating the model training and evaluation workflows with reproducibility and traceability in mind.
• Defining infrastructure standards and best practices for ML experimentation, CI/CD, and observability.
• Collaborating with ML researchers and engineers to improve productivity through tooling and platform enhancements.

You thrive in fast-paced, dynamic environments and are comfortable navigating ambiguity to deliver meaningful, incremental impact. You bring strong problem-solving skills, operate with a high degree of autonomy and have a track record of executing effectively. With a commitment to continuous learning and attention to detail, you actively seek opportunities to innovate and share knowledge. You follow engineering best practices - including unit testing, CI/CD, documentation, monitoring, and alerting - to ensure reliable, maintainable solutions.

• 7 years of development experience and Bachelors or Masters degree in Computer Science or 5 years development experience and PhD in Computer science or related field, with at least 3 years focused on large-scale machine learning infrastructure
• Proficient in Python with solid knowledge of software design principles.
• Expertise in designing and implementing distributed systems or data pipelines (e.g., Spark, Flink, Kafka, Airflow) and knowledge of SQL to analyze data and derive insights.
• Experience with ML lifecycle tools (e.g., MLflow, Metaflow, Kubeflow, SageMaker, Vertex AI).
• Hands-on experience with container orchestration and cloud-native services (e.g., Kubernetes, Docker, AWS/GCP/Azure).
• Leadership experience, including being a technical lead for complex, cross functional development projects demonstrating good technical judgement and prioritization skills. Strong communication skills and a proactive, ownership-driven mindset.

• Prior experience architecting ML platforms or Feature Stores in a fast-paced production environment.
• Experience with real-time model serving and streaming pipelines (e.g., Kafka, Flink, Ray Serve, Triton).
• Experience optimizing GPU and CPU resource allocation for training and inference workloads.
• Experience with any ML authoring framework (PyTorch, TensorFlow, JAX, etc.), particularly on-device ML frameworks such as CoreML, TFLite or ExecuTorch.