Design a recommendation system end-to-end
Company: OpenAI
Role: Machine Learning Engineer
Category: ML System Design
Difficulty: hard
Interview Round: Onsite
## Question
Design a large-scale recommendation system (e.g., short videos or e-commerce items).
## Requirements
- Personalized feed ranking for hundreds of millions of users.
- Handle cold start for new users/items.
- Near real-time adaptation to user actions.
- Optimize for long-term engagement while controlling for harmful feedback loops.
## Deliverables
- Candidate generation + ranking architecture.
- Feature pipelines (real-time and batch).
- Training, serving, and evaluation (metrics + experimentation).
- Monitoring and guardrails (fairness, spam, safety).
Quick Answer: This question evaluates a candidate's competency in large-scale machine learning system design, including architecture for candidate generation and ranking, feature engineering across real-time and batch pipelines, training and serving workflows, and monitoring for fairness and safety.