Skip to content
tezvyn:

LLMs & Generative AI

Large language models, chatbots, agents, prompt engineering

145 bites

Test yourself: Top 30 LLMs & Generative AI interview questionsMultiple choice, with the correct answer and why it is correct on every question. Free, no sign-in.

Interview questions in LLMs & Generative AI, page 6

intermediate2 min read

Agent planning beyond a ReAct loop

ReAct adapts step by step but costs many calls, plan-then-execute drafts a full plan upfront for fewer calls but is brittle to surprises, hierarchical decomposition splits goals…

intermediate2 min read

Detecting catastrophic forgetting in continual fine-tuning

Maintain a frozen held-out benchmark of original capabilities, evaluate after every fine-tune, track per-capability deltas, and alert on regressions.

intermediate2 min read

Dynamic batching and the throughput-latency trade-off

The server groups concurrent requests into one batch to use the GPU fully, but larger batches and waiting to fill them raise per-request latency and time to first token.

intermediate2 min read

Handling outlier activations in INT8 quantization

Profile activation magnitudes to find a few large-magnitude outlier channels, then keep those in higher precision while quantizing the rest, a mixed-precision decomposition.

intermediate1 min read

Mitigating demographic bias in a fine-tuned chatbot

Curate or counterfactually augment training data to balance demographics, plus apply post-hoc guardrails or fairness-constrained fine-tuning.

intermediate1 min read

Preprocessing conversations to protect privacy before fine-tuning

Detect and redact PII with NER plus regex, choose redaction versus pseudonymization, and validate recall.

intermediate1 min read

Measuring fairness in an embedding-based text classifier

Define group definitions, apply demographic parity and equalized odds, and address noisy labels and implicit group membership.

intermediate1 min read

Practical explainability for an LLM loan summary

Use attribution-by-design with grounded citations, structured rationales, and a deterministic rules layer instead of slow per-token SHAP.

intermediate1 min read

Data lineage and machine unlearning for a fine-tuned LLM

Version and fingerprint datasets, record transforms and which checkpoint saw what, and enable unlearning via retraining, data sharding, or approximate gradient methods.

intermediate2 min read

Designing an autonomous research-and-report agent

Planner that decomposes goals, short-term scratchpad plus long-term vector memory, structured tool calls, and a reflect-retry loop for error correction.

intermediate2 min read

Why RAG persists despite million-token context windows

Cost and latency scale with context, attention degrades in the middle, and RAG adds freshness, access control, and citations.

intermediate2 min read

Self-attention and the Query, Key, Value matrices

Queries score against keys via scaled dot product, softmax yields weights, and those weight the values into the output.

intermediate1 min read

How Transformers encode token position

Attention is permutation-invariant, so positional encodings (sinusoidal, learned, or rotary) are added or applied.

intermediate1 min read

Cross-attention versus self-attention in encoder-decoder Transformers

Cross-attention draws Queries from the decoder and Keys/Values from the encoder, letting the decoder condition on the source.

intermediate2 min read

Tokens and vocabulary-size tradeoffs

A token is a subword unit; larger vocab shortens sequences but bloats the embedding matrix, smaller vocab generalizes but lengthens sequences.

intermediate2 min read

Fault-tolerant checkpointing for thousand-GPU pre-training

Checkpoint weights, optimizer state, RNG, and data position together; use asynchronous sharded writes and automated detect-restart-resume.

intermediate2 min read

Prompt engineering to curb extraction hallucinations

Ground strictly in source, allow null for missing fields, enforce a schema, and use few-shot examples; acknowledge prompting cannot fully eliminate it.

intermediate2 min read

Self-consistency over chain-of-thought

Sample multiple CoT paths at nonzero temperature and majority-vote the final answer; cost scales with the number of samples.

intermediate2 min read

Why chain-of-thought helps large models but not small ones

Small models lack reliable multi-step reasoning, so CoT just adds error-prone steps; adapt by using few-shot/fine-tuning or distillation for small tiers.

intermediate2 min read

Handling a 401 error in an LLM agent's tool call

Catch the tool error, return a structured observation to the LLM, and distinguish recoverable retries from terminal failures needing re-plan or escalation.

We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.

See open roles