Interview Practice Questions

Design an architecture for an NER system that should support 10,000 concurrent users and process 100,000 documents per day. How will you handle latency and scalability?

Design a semantic search system that should handle 5 million documents and provide search results with a latency of less than 200 ms. What are your recommendations for architecture and data storage?

Design a system that handles requests to a chatbot with 10,000 active users simultaneously. Consider a response time of no more than 300 ms and an infrastructure budget of $5,000 per month. What will your architecture look like?

You need to build a document classification system with a data volume of 1 million documents and a processing latency of no more than 1 second. What approach will you take for model training, and what architecture will you propose?

Design a system for named entity recognition from texts with a data volume of 10,000 documents per day. Consider the need to maintain an accuracy of at least 85% and a processing time of no more than 200 ms per document. What technologies will you use?

You need to build a search engine that processes 500 QPS from users and supports both semantic and keyword search. How will you organize data storage and indexing considering a budget of $10,000 per month?

Design a text summarization system that handles 1,000 requests per minute with a maximum latency of 500 ms. What architecture will you propose to ensure quality summaries?

You need to build a system for serving an LLM that will serve 1,000 concurrent users with a latency of no more than 100 ms. What will be your key architectural and scaling considerations?

Design a RAG pipeline that processes 200 QPS and achieves query accuracy of at least 90%. How will you organize the components, and what technologies will you use?

Design a content moderation system for a platform with 5 million users, ensuring content checks with a maximum response time of 1 second and a minimum accuracy of 95%. What approaches and technologies will you apply?

Design a document classification system that needs to process 100,000 documents per day and achieve an accuracy of at least 85%. The system should be designed with scalability in mind to handle up to 1,000,000 documents per day in the future. Please discuss the architecture, data processing approaches, and model selection.

You need to build a chatbot that will serve 10,000 active users concurrently with a response time of less than 2 seconds for each query. The bot should support both natural language conversations and FAQs. Please discuss the necessary system components, their interactions, and approaches to query processing.

Design a recommendation system for an e-commerce platform that can handle 100,000 concurrent users and provides a response time of less than 200 ms per query. You have a budget of $50,000 for infrastructure and a team of 5 people. What key components would you utilize?

Design a recommendation system for a music streaming service that must handle 10 million users with 1000 QPS and provide personalized playlists. What architecture would you propose to ensure scalability and low latency?

Design a news feed ranking system that must update in real-time for 5 million users with a latency limit of no more than 500 ms. How will you handle new articles and account for user preferences?

Design a 'similar items' recommendation system for an e-commerce platform that must handle 50 million products and 20 million users. Response time should be no more than 100 ms. What algorithms and methods would you apply?

Design an ad targeting system that must provide high relevance for 10 million users in real-time with a query rate of 5000 QPS. How will you incorporate user data and their actions?

Design a 'people also bought' system for an e-commerce platform that must handle 30 million users and 100 million products, with latency of no more than 300 ms. What data and metrics will you use to build the model?

Design a personalized email marketing system for 5 million users that must be tailored to user preferences and achieve high open rates. How will you manage user data and their behaviors?

Design a recommendation system for a video streaming service that must handle 15 million users and ensure response times of less than 200 ms per query. What approaches will you use to implement this project?