Senior Machine Learning Engineer, Wallet, Payment & Commerce

Apple Apple · Big Tech · Austin, TX +1 · Software and Services

Senior Machine Learning Engineer for Apple Wallet, Payment & Commerce team, focusing on building end-to-end ML solutions for security, fraud prevention, and operational efficiency. The role involves the full ML lifecycle from data collection and feature engineering to model implementation, evaluation, and performance reporting, with a strong emphasis on privacy-preserving techniques and collaboration with cross-functional teams.

What you'd actually do

  1. Prevent fraud, improve security, and drive operational efficiency across company platforms including Apple Wallet by designing and delivering end-to-end machine learning and data science solutions, leveraging classification, anomaly detection, behavioral modeling, and feature engineering techniques.
  2. Partner with software engineers, security engineers, program managers, and business stakeholders to define problems, develop data-driven solutions, implement execution plans, and communicate results on a regular cadence to both technical and non-technical audiences.
  3. Own the full ML lifecycle for assigned problem domains; translating business and customer needs into production systems through feature engineering, model implementation, training, evaluation, and performance reporting, applying deep expertise in machine learning and data science to deliver innovative, production-quality solutions in an agile environment.
  4. Lead project planning and end-to-end program management of data collection initiatives for Wallet machine learning programs, including requirements gathering, scope definition, prioritization, vendor coordination, resource allocation, and scheduling of deliverables; collaborate with privacy, legal, and research partners to ensure data collection practices comply with regulatory, ethical, and informed consent requirements, including IRB processes where applicable.
  5. Drive improvements to data operations across supported ML features; increasing dataset diversity and quality while reducing acquisition lead time and cost through scalable workflows that combine human annotation pipelines and automated machine computation, incorporating advances in ML modeling approaches.

Skills

Required

  • Master's degree in Computer Science, Statistics, Machine Learning, or equivalent field (e.g., Business Analytics with quantitative focus).
  • At least five years of industry experience deploying machine learning algorithms — including classification, clustering, and anomaly detection — to support customer-facing features in production environments.
  • Deep expertise working with relational databases and SQL, and large-scale distributed computing systems such as Hadoop and Spark.
  • Strong programming skills in one or more of the following languages: Python, Scala, or Java; familiarity with Objective-C or Swift for on-device model deployment contexts.
  • Experience with ML workflow and data management tooling, including workflow orchestration frameworks (e.g., Airflow), distributed compute frameworks (e.g., Ray), experiment tracking platforms (e.g., Weights & Biases), and ML model development frameworks (e.g., Turi Create).
  • Experience implementing privacy-preserving techniques on production data pipelines and ML models across multiple projects.
  • Experience in data acquisition program management, including working with external vendors and procurement teams, and designing and executing user studies to build high-quality labeled datasets.
  • Domain expertise in fraud detection, risk modeling, or security-focused machine learning applications.

Nice to have

  • Experience with the secure handling, processing, and governance of sensitive personal data in production ML systems.
  • Experience integrating device-based signals and features into risk models, including identification of device-based fraud risk indicators.
  • Prior experience with Institutional Review Board (IRB) processes, informed consent frameworks, and the design and execution of user studies for data collection purposes.
  • Demonstrated history of measurable business impact through fraud prevention with minimal disruption to the legitimate customer experience.
  • Familiarity with internal datasets, tooling, and systems relevant to payments, Wallet, and fraud decisioning.

What the JD emphasized

  • end-to-end machine learning and data science solutions
  • production systems
  • privacy-preserving techniques
  • fraud detection
  • security

Other signals

  • end-to-end machine learning and data science solutions
  • production systems
  • fraud detection
  • security