Design a large-scale Feed Generation Platform
Last updated: May 15, 2026
Quick Overview
Design a scalable feed generation system that handles millions of requests. Discuss trade-offs in consistency, availability, and performance.
Databricks
System Design
Software Engineer
Databricks
May 15, 2026Software Engineer
Onsite
System Design
Medium
1
6
3,703 solved
Design a scalable feed generation system that handles millions of requests. Discuss trade-offs in consistency, availability, and performance.
Databricks asks this during the Onsite to assess your understanding of the full ML lifecycle. They want to see how you translate a business problem into an ML objective, design the feature pipeline, and plan for model monitoring and retraining.
What the Interviewer Expects
- Define clear ML objectives with appropriate loss functions and metrics
- Design a comprehensive feature engineering pipeline
- Discuss model selection with trade-offs (complexity vs interpretability vs latency)
- Plan online and offline evaluation strategies including A/B testing
- Address serving infrastructure: batch vs real-time, latency requirements
- Consider data quality, labeling strategy, and feedback loops
Key Topics to Cover
Model selection and architecture
Feature engineering and feature stores
Model serving and latency optimization
Monitoring and model degradation detection
A/B testing and experimentation
Feedback loops and model retraining
How to Approach This
- Start by clarifying functional and non-functional requirements with the interviewer.
- Estimate the scale: QPS, storage, bandwidth. This drives your design decisions.
- Draw a high-level architecture first, then deep dive into 1-2 critical components.
- Discuss trade-offs explicitly (e.g., consistency vs availability, SQL vs NoSQL).
- Address failure scenarios, monitoring, and how the system handles 10x traffic spikes.
Possible Follow-up Questions
- How would you run A/B tests on different model versions?
- How would you handle a 10x increase in prediction requests?
- What would you do if model performance degrades over time?
Practice a Similar Problem on Codemia
Solve a related problem with our interactive workspace, get AI feedback, and view detailed solutions.
Solve on CodemiaSample Answer
Requirements
- Functional Requirements:
- The system should generate personalized feeds for users based on their interactions and preferences.
- Support for real-time updates to the feed upon user interact...
Capacity Estimation
To estimate capacity, assume:
- User Base: 10 million active users.
- Requests per User: Each user interacts with the feed 20 times per day.
- Total Requests: 10 million users * 20 interac...
Submit Your Answer
Markdown supported