Machine Learning Engineer - Strategic Data Solutions (Retail Fraud)

Imagine what you could do here. At Apple, new ideas have a way of becoming outstanding products, services, and customer experiences very quickly. Bring passion and dedication to your job, and there's no telling what you could accomplish.

Apple's Strategic Data Solutions (SDS) team is looking for a hardworking individual who is passionate about crafting, implementing, and operating analytical solutions that have a direct and measurable impact on Apple and its customers.

As an SDS Machine Learning Engineer, you will employ predictive modeling and statistical analyses to build end-to-end solutions for improving security, fraud prevention, and operational efficiency across the company, from manufacturing to fulfillment to apps and services.

Apple's dedication to customer privacy, the adversarial nature of fraud, and the enormous scale of the business present exciting challenges to traditional machine learning and data science techniques. On this team, we will push the limits of existing data science methods while delivering tangible business value!

Description

Engage with business teams to find opportunities, understand requirements, and translate those requirements into technical solutions.

Design a data science approach, applying tried-and-true techniques or developing custom algorithms as needed for the business problem.

Collaborate with data engineers and platform architects to implement robust production real-time and batch decisioning solutions.

Ensure operational and business metric health by monitoring production decision points.

Investigate adversarial trends, identify behavior patterns, and respond with agile logic changes.

Communicate results of analyses to business partners and executives.

Minimum Qualifications

Education in a quantitative field, such as Computer Science, Applied Mathematics, or Statistics, or equivalent professional experience.

Practical experience with and theoretical understanding of algorithms for classification, regression, clustering, and anomaly detection.

Working knowledge of relational databases, including SQL, and large-scale distributed systems such as Hadoop and Spark.

Ability to implement data science pipelines and applications in a general programming language such as Python, Scala, or Java.

Preferred Qualifications

Ability to comprehend and debug complex systems integrations spanning toolchains and teams.

Ability to extract meaningful business insights from data and identify the stories behind the patterns.

Excellent presentation skills, distilling complex analysis and concepts into concise business-focused takeaways.

Creativity to engineer novel features and signals, and to push beyond current tools and approaches.

Experience working building and work with integrated LLM architectures.