Skip to content
tezvyn:

🤖AI & ML

Artificial intelligence, machine learning, and data science

1166 bites

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

Everything in AI & ML, page 2

intermediate1 min read

Directed Acyclic Graph (DAG) for Workflows

A DAG models a workflow as tasks (nodes) connected by dependency edges with no cycles, so a scheduler knows the valid execution order. It enables parallelism, safe retries, and idempotent reruns, and underpins orchestrators like Airflow for ML pipelines.

intermediate1 min read

Staging Environments for ML Pipelines

A staging environment mirrors production so models and pipelines are validated on production-like data and infrastructure before release. It catches drift, integration breaks, and serving regressions early, making promotion to production a safe, repeatable…

intermediate1 min read

AWS Bedrock versus a direct provider API

Bedrock unifies many models with IAM, VPC, and cloud integration; a direct provider API gives earliest models, full feature parity, and simpler vendor terms.

intermediate1 min read

Designing an LLM red-teaming framework

Taxonomy of harms, automated adversarial prompt generation via attacker models and mutation, a classifier to triage outputs, and severity-by-likelihood prioritization.

intermediate1 min read

Scalable oversight of superhuman models

Humans cannot judge outputs beyond their expertise, so feedback degrades; techniques like AI debate or recursive reward modeling decompose judgment.

intermediate1 min read

The alignment tax and capability trade-offs

Alignment tax is capability lost from safety tuning, measured as benchmark or task-success deltas before and after; a product decision weighs over-refusal against harm risk.

intermediate1 min read

Penalizing sycophancy in a reward model

Sycophancy is reward proxy gaming where agreeableness substitutes for correctness; counter it with truth-anchored labels, perturbed-premise pairs, and consistency checks.

intermediate1 min read

Constitutional AI versus standard RLHF

A written principle set guides self-critique and revision, plus AI feedback (RLAIF) replaces human preference labels.

intermediate2 min read

Preventing PII in LLM outputs: curation, fine-tuning, or guardrails

Favor post-processing guardrails as the enforceable last line, backed by data curation; note each layer's tradeoffs and that defense-in-depth is best.

intermediate2 min read

Red teaming a generative model

Deliberately probe for harmful outputs across categories, document jailbreaks, and automate with adversarial prompt generators plus classifier-based judging.

intermediate2 min read

Evaluating faithfulness and compositionality in multimodal models

Use targeted probes with hard negatives, attribute-relation binding tests, and structured grounding checks; note BLEU rewards surface overlap not correctness.

intermediate2 min read

CLIP's contrastive objective and zero-shot classification

Train image and text encoders to align matched pairs and repel mismatched ones in a shared space; classify zero-shot by comparing an image to text prompts of class names.

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.

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

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

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

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

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.

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.

intermediate1 min read

How Transformers encode token position

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

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