Machine Learning Engineer — Trust and Safety (account Trust)

Apple Apple · Big Tech · Austin, TX +1 · Machine Learning and AI

Machine Learning Engineer focused on Trust and Safety for communication apps, protecting against spam and abuse. The role involves building ML tooling for the entire ML lifecycle, from data ETL and model training to evaluation and deployment, with a strong emphasis on anti-fraud and anomaly detection, particularly in the context of LLMs. The goal is to deliver reusable tooling and integrate with existing systems to enhance customer safety and mitigate attack vectors.

What you'd actually do

  1. Build machine learning tooling to facilitate various phases of the ML lifecycle from model training, data ETL, end-to-end model evaluation and deployment.
  2. Deliver reusable and easy-to-use tooling to integrate with existing data and machine learning systems.
  3. Identify weaknesses, propose better fraud-fighting tools, and anticipate attacker adaptations.
  4. Build strong partnerships to close data gaps and mitigate attack vectors.
  5. Simplify complex systems and work with technical and non-technical stakeholders to build solutions to align for specific use cases.

Skills

Required

  • Python
  • machine learning algorithms
  • classifiers
  • clustering algorithms
  • anomaly detection
  • LLMs
  • big data tools
  • SQL
  • Spark
  • Splunk
  • Jupyter Notebook
  • collaboration

Nice to have

  • Scala
  • Java
  • scikit-learn
  • TensorFlow
  • PyTorch
  • Spark MLlib
  • industry software development
  • source control
  • Git
  • MS/PhD in quantitative field
  • scalable deep learning systems
  • large scale data infrastructure

What the JD emphasized

  • Proven experience in anti-fraud (or similar) with at least two complex investigations in incomplete data environments, demonstrating initiative and measurable impact.
  • Strong understanding of machine learning algorithms (including classifiers, clustering algorithms, and anomaly detection), especially in the context of LLMs.
  • Experience collaborating across engineering and non-engineering teams.

Other signals

  • anti-fraud
  • LLMs
  • anomaly detection
  • ML lifecycle