Software Engineer - Athena Synapse, Is&t AI & Data Platforms

Apple Apple · Big Tech · Shanghai, Shanghai, China · Software and Services

Software Engineer on the Athena platform at Apple, responsible for building and maintaining data services and platforms that support machine learning analytics for fraud, waste, and abuse prevention. The role involves developing scalable systems for both near-real-time decisioning and batch analytics, focusing on operational excellence, low-latency services, automated pipelines, and model health.

What you'd actually do

  1. Turn business and ML requirements into scalable platform and decisioning systems
  2. Build resilient, low-latency services for real-time inference and streaming data
  3. Define gold-standard CI/CD, observability, and SLA practices for Data and ML
  4. Ship automated pipelines powering features, training, and online serving
  5. Drive performance and cost optimizations across Data and ML workloads

Skills

Required

  • Java, Python, or Scala
  • Spark, Flink, Kafka, or similar distributed data technologies
  • Designing, optimizing, and debugging large-scale production data pipelines
  • Systems thinking, communication, and problem-solving skills

Nice to have

  • ML/AI platforms, including feature engineering, model training, or GenAI workflows
  • Kubernetes and cloud-native technologies
  • Alibaba Cloud or other cloud platforms in regulated or region-specific environments, including PIPL
  • Mentoring engineers and driving technical collaboration

What the JD emphasized

  • 5+ years building production-grade software or data platforms at scale
  • Experience with ML/AI platforms, including feature engineering, model training, or GenAI workflows
  • Experience with Alibaba Cloud or other cloud platforms in regulated or region-specific environments, including PIPL

Other signals

  • building data services and platforms that run machine learning analytics
  • Athena is a machine learning platform
  • supporting both online solutions for near-real-time decisioning, and offline solutions for batch analytics and reporting
  • Build resilient, low-latency services for real-time inference and streaming data
  • Ship automated pipelines powering features, training, and online serving
  • Drive performance and cost optimizations across Data and ML workloads
  • Own data and model health with monitoring, validation, and drift detection