Agent skill · research science · aradotso
ai-engineering-interview-questions
ai-engineering-interview-questions — an agent skill for coding agents.
Why this skill is useful
Provides a comprehensive collection of niche AI engineering interview questions and answers that the AI wouldn't generate on its own.
What it needs
About 10k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash Clone the repo locally for offline study git clone https://github.com/amitshekhariitbhu/ai-engineering-interview-questions.git cd ai-engineering-interview-questions Browse the main README cat README.md Or open in your editor code README.md Key Concepts: Transformer architecture: encoder-only, decoder-only, encoder-decoder Self-attention: Q (Query), K (Key), V (Value) matrices Multi-head attention vs Grouped-Query Attention (GQA) Tokenization: BPE, WordPiece, SentencePiece Positional encoding (absolute, learned, RoPE) KV Cache: speeds up autoregressive inference by caching past K/V Mixture of Experts (MoE): sparse routing to expert sub-networks Flash Attention: memory-efficient attention with IO-aware tiling Context window: maximum tokens the model can process at once Temperature, Top-k, Top-p: controls for text generation randomness Attention(Q, K, V) = softmax(QK^T / sqrt(dk)) V Q, K, V are learned linear projections of the input Scaled dot-product prevents vanishing gradients in softmax Multi-head: run H attention heads in parallel, concatenate outputs During autoregressive generation: Without cache: recompute K, V for ALL previous tokens each step → O(n²) With KV cache: store K, V for previous tokens, only compute new token → O(n) Trade-off: memory grows linearly with sequence length [User Query] │ ▼ [Embedding Model] → Query Vector │ ▼ [Vector DB Search] → Top-K Chunks │ ▼ [Re-ranker] (optional) → Reordered Chunks │ ▼ [LLM] + [System Prompt] + [Retrieved Context] + [User Query] │ ▼ [Response] 1. Document Ingestion Load → Parse → Chunk → Embed → Store in Vector DB 2. Chunking Strategies Fixed-size: simple, predictable, may break context Recursive: respects document structure (headers, paragraphs) Semantic: groups semantically similar sentences together 3. Retrieval Dense (vector similarity): semantic search via embeddings Sparse (BM25/TF-IDF): keyword matching Hybrid: combine both with RRF (Reciprocal Rank Fusion) 4. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/ai-engineering-interview-questions