Design a news feed ranking system
Quick Overview
This question evaluates a candidate's ability to architect a scalable, low-latency personalized news feed recommendation system, assessing competencies in candidate generation, ranking and post-ranking, embedding design and serving, data logging, and experimental evaluation.
Apple
Mar 1, 2026, 12:00 AM
Machine Learning Engineer
Technical Screen
ML System Design
2
0
Loading...
Design a personalized news feed recommendation system.
Requirements:
- Low latency serving (real-time feed generation).
- Personalization using user behavior and content features.
- Freshness and diversity (avoid showing only one topic/source).
In your design, explain:
- High-level architecture (candidate generation, ranking, post-ranking).
- Data/logging needed for training and evaluation.
-
How you would generate and serve
embeddings
(user/item/content embeddings):
- How embeddings are trained.
- How they are updated (batch vs near-real-time).
- How the online service fetches/uses them (feature store vs embedding store).
- How you evaluate the system offline and online (A/B tests, metrics, guardrails).
Solution
Show