Amazon·Software Engineer·Online Assessment (OA)
May 2026
Amazon SWE coding round where the main task was implementing a GPT model from scratch, including the attention mechanism, feedforward layers, and the full decoder stack. Pretty involved for what felt like a coding screen.
- Implement a basic GPT model with MultiheadAttention, Feedforward, DecoderLayer, and GPT classes. The model should support forward propagation given parameters like vocabulary size, embedding dimension, number of layers, number of heads, dropout rate, and sequence length.
“I knew the high-level architecture but writing it out class by class under time pressure was rougher than expected.” The rest of the author's notes on Software Engineer interview at Amazon, Online Assessment (OA) round, covers how they worked through the question, what the panel pushed back on, and what they would do differently.
View Post