Fresher / New Grad

Pick the right vector database for a startup with 2M documents, no DevOps headcount, and a one week launch deadline.

Define recall@10 for a vector index, and spell out exactly what 'ground truth' means in that definition.

pgvector ships two index types. Which should be your default reach in 2026, and why was it added later than the other?

Fill in the IVF nlist rule of thumb.

Explain exactly what the ef_search knob on an HNSW index controls at query time.

Where does Hamming distance become the natural metric inside a vector database, and how is it implemented efficiently?

Name two situations where Flat brute force search is still the correct production choice in a 2026 vector pipeline.

Select all dimensions that meaningfully drive cost on a managed vector database bill in 2026.

Cosine similarity and dot product give identical rankings under exactly one condition. Which is it?

Why does every production retrieval system use approximate nearest-neighbor search instead of exact search past a certain corpus size?

Complete the RMSNorm formula

Why does a deep transformer stack stop training if you remove the residual connections?

Describe the residual stream as a read/write surface that sublayers act on

Pair each transformer family with its canonical pretraining objective

Spot the error: 'The FFN mixes information across tokens'

Why does the transformer block use LayerNorm or RMSNorm instead of BatchNorm?

Define d_model and name three architecture knobs that scale with it

What does 'position-wise' actually mean for the transformer FFN sublayer?

Which sublayer of a dense transformer block carries more parameters, attention or FFN?

Pick the 2026 task where an encoder-only transformer still beats a decoder-only LLM

Name a 2026 task where an encoder-decoder transformer still beats a decoder-only LLM

Complete the pre-norm transformer block recipe

Order the operations inside a single pre-norm transformer block forward pass

Why production chat UIs stream tokens token by token instead of returning the full reply

Each decode step loads ___ from HBM, regardless of how many tokens have already been generated