Machine Learning Engineer - ML Systems and Evaluation Engineering

At Apple, diverse perspectives and collaborative innovation drive breakthrough products that impact millions of lives worldwide. We believe that bringing together individual creativity with shared values creates technology that truly matters. Here, you'll contribute your unique expertise while helping build the future of AI-powered experiences. The ML Systems Evaluation Engineering (MLSEE) team, part of the Siri and VPG Software organization, is at the forefront of machine learning and Generative AI evaluation. We develop cutting-edge evaluation technologies and methodologies that ensure the quality and reliability of conversational AI assistants and AI agents across Apple's ecosystem - from large-scale cloud infrastructure to personal devices. Our mission is critical: we build the evaluation platforms and tools that gate the quality of AI/ML products before they reach millions of users globally. By joining our team, you'll play a direct role in shaping how Siri, AI agents, and other AI products deliver exceptional experiences that help people accomplish their goals every day.

Description

We're seeking a solution-oriented machine learning engineer with strong software development skills to architect, build, and maintain innovative evaluation platforms and tools for large-scale statistical assessment of GenAI-powered products, models, and AI agents. As a key member of our team, you'll deliver evaluation-as-a-service solutions that empower product and modeling teams across Apple to run comprehensive statistical evaluations, generate actionable metrics and insights, and make informed shipping decisions. What You'll Do: Partner with cross-functional teams to translate evaluation needs into robust technical solutions for conversational AI, language models, and AI agent capabilities Own end-to-end requirements gathering, proof-of-concept development, and co-drive the development roadmap for ML system evaluation platforms Design and implement scalable solutions that enable statistical analysis of product experiences, model performance, and AI agent behavior at scale Drive system integration efforts and influence how evaluation software is incorporated into ML model and AI agent CI/CD pipelines Develop monitoring and observability solutions to provide deep insights into platform performance, evaluation quality, and AI agent reliability Build specialized evaluation frameworks for AI agents, including multi-step reasoning assessment, tool usage validation, and agent interaction quality measurement * Iterate rapidly based on stakeholder feedback while maintaining platform reliability and performance across diverse AI workloads The ideal candidate thrives in fast-paced environments, combines strategic thinking with hands-on problem-solving, and is passionate about enabling data-driven decisions that enhance Apple product experiences for millions of users. You'll be instrumental in building the next generation of evaluation infrastructure that supports Apple's expanding AI agent capabilities.

• 10+ years of professional software development experience with demonstrated expertise in designing, implementing, and optimizing large-scale, data and compute-intensive frameworks, APIs, and tools
• Strong full-stack software engineering capabilities including system design, backend development, testing, debugging, release management, and production maintenance
• Expert-level proficiency in Python (required) and at least one additional object-oriented programming language (e.g., Swift, Java, Go)
• Solid experience with service-oriented architecture and distributed systems design patterns
• Backend development expertise with experience building scalable APIs, microservices, and platform infrastructure
• Bachelors in Computer Science or related degree

• Statistical evaluation methodology knowledge including experience with ML training pipelines, model accuracy assessment, performance optimization techniques, and AI agent evaluation frameworks
• Platform and infrastructure mindset with ability to develop long-term strategic visions and execute scalable solutions in agile, fast-paced work environments
• Cross-functional collaboration skills with strong organizational abilities and experience working effectively with multiple stakeholders across product, engineering, and research teams
• Communication excellence with demonstrated ability to document complex technical concepts and present solutions to diverse audiences
• ML lifecycle familiarity including exposure to data preprocessing, model training, evaluation methodologies, deployment strategies, monitoring approaches, and AI agent development workflows
• AI agent evaluation experience including familiarity with agentic workflows, multi-step reasoning assessment, tool usage validation, and autonomous system reliability measurement
• MS in Computer Science, Software Engineering, or related technical field preferred