Google·Software Engineer·Technical Phone Screen
Jun 2026
Conceptual LLM interview at Google for a software engineering role, covering Transformer architecture, fine-tuning strategies, and inference-time steering. No coding, just reasoning through trade-offs, which honestly felt harder in some ways.
- Walk through how a decoder-only Transformer converts input tokens into a next-token prediction. Cover the query/key/value projections, how attention weights are formed, why multiple heads are used, how position is encoded, what the feed-forward sublayers do, and why attention cost scales quadratically with sequence length.
- What does 'post-training' mean, and why is a raw pretrained base model usually not useful as a product assistant straight out of the box?
- Compare supervised fine-tuning with preference-based optimization methods like RLHF and DPO. What problem does each solve and how do they differ mechanically?
- Compare full fine-tuning against parameter-efficient methods like LoRA. What does LoRA actually train, and what practical advantages does that give you?
- Given a new task with limited labeled data and a cost/latency budget, how do you decide between prompting, retrieval-augmented generation, and fine-tuning?
- With a fully frozen hosted model, what levers do you have to steer its behavior? Cover zero-shot, few-shot, chain-of-thought prompting, system prompts, structured output elicitation, and RAG.
- How does the quadratic attention cost relate to context window limits in practice, and what techniques exist to reduce it?
- What is catastrophic forgetting and how does it factor into choosing between full fine-tuning and LoRA?
- A model confidently states a false fact. How do you diagnose whether the fix is a prompt change, RAG, or fine-tuning?
- How would you actually evaluate whether a fine-tune or a prompt change improved the product, beyond manually checking a few outputs?
“This is a lot to hold in your head at once.” The rest of the author's notes on Software Engineer interview at Google, Technical Phone Screen round, covers how they worked through the question, what the panel pushed back on, and what they would do differently.
View Post