Compare Transformers and RNNs and Derive Attention Complexity
Company: C3 AI
Role: Data Scientist
Category: Machine Learning
Difficulty: hard
Interview Round: Technical Screen
Overview: Compare Transformers and RNNs while deriving dense self-attention complexity. Separate projection and score costs, training parallelism, generation caching, long context, and streaming trade-offs.
Read the full C3 AI Data Scientist interview experience this question came from