Apple's iCloud Anti-Abuse team protects hundreds of millions of users from spam, phishing, and malicious content across Mail, Calendar, and Contacts.
We are looking for an ML engineer who can build and ship models in production distributed systems. You will design, train, and deploy ML models that operate at iCloud scale, working across the full lifecycle from data pipelines to real-time inference. You will partner with backend engineers and cross-functional teams in trust and safety, operations, and product to deliver measurable improvements in user protection.
Description
This role sits at the intersection of machine learning and distributed systems engineering. You will play a foundational role in building the team's ML capabilities — owning ML-driven abuse detection: building features from high-volume data streams, training and evaluating classification and ranking models, deploying them into low-latency serving infrastructure, and closing
the feedback loop. The systems you build will run at massive scale across Apple's infrastructure.
Success in this role means writing production-quality code, reasoning about distributed system tradeoffs, and iterating quickly on model performance.
This is a high-impact role — your work will directly determine whether abuse reaches iCloud users or gets stopped.
Minimum Qualifications
3+ years of hands-on machine learning engineering experience, including training and deploying models in production
Strong programming skills in one or more production languages (e.g., Java, Scala, Kotlin, Go, Python)
Experience building and operating ML pipelines: data processing, feature engineering, training, serving, and monitoring
Solid foundation in distributed systems — you can reason about scalability, fault tolerance, and latency tradeoffs
Familiarity with classification, ranking, or anomaly detection techniques
Ability to drive projects independently from problem definition to production
BS in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience
Preferred Qualifications
5+ years of ML engineering experience (or equivalent depth) with models running at scale in production
Experience with abuse detection, fraud prevention, content filtering, or trust and safety systems
Expertise in NLP or text classification applied to email, messaging, or similar domains
Experience with streaming/real-time ML inference in addition to batch processing
Familiarity with techniques for scoring, ranking, or classifying actors and behaviors at scale
Understanding of privacy-preserving ML techniques and responsible data handling
Experience with email protocols (SMTP, IMAP) or messaging infrastructure
MS/PhD in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience
