AI Engineering Interview Questions — Practice Library | Velocode

300+ problems

Problem

Tags

Type

Hierarchical cache breakpoints: system prompt, tool definitions, context windows, query batches

Reported at CursorAI EngineeringMedium

LLM output validation with schema enforcement and type checking

Reported at MetaSWE (AI-Era)Medium

Support Agent Replies in the Wrong Language

Forward DeployedEasy

Code Comprehension

Document chunking for vector databases with sentence-boundary preservation

Reported at PerplexitySWE (AI-Era)Easy

Conversation History Compression for Long-Running Agents

Reported at AnthropicSWE (AI-Era)Hard

Re-Architect Retrieval to Scale to 2 Million Documents

Forward DeployedHard

Evaluation Metric Misalignment: Faithfulness Scores Mask Semantic Errors

Reported at AnthropicAI EngineeringMedium

Code Comprehension

Retrieval deduplication: chunks from same document not filtered before ranking.

Reported at PineconeAI EngineeringMedium

Code Comprehension

Build a Robust CSV Importer for Messy Customer Data

Forward DeployedEasy

Prompt Injection Vulnerability in Content Filter Implementation

Reported at AnthropicSWE (AI-Era)Medium

Code Comprehension

Hallucination Detection Pipeline Fails On Contradictory Claims Against Context

Reported at Scale AIAI EngineeringMedium

Code Comprehension

Capstone: Build, Debug, and Secure a Returns Agent, Then Brief the Launch

Forward DeployedHard

RAG Pipeline Missing Document Metadata During Chunk Ingestion

Reported at CohereAI EngineeringEasy

Code Comprehension

Resilient LLM API calls with exponential backoff retry logic

Reported at AnthropicSWE (AI-Era)Easy

Agent Calls the Wrong Tool

Forward DeployedMedium

Code Comprehension

Stream Aggregator Batches LLM Tokens Into Complete Sentences

Reported at GoogleSWE (AI-Era)Medium

Multi-tenant RAG: Secure Vector Index Isolation for Enterprise

Reported at OpenAIAI EngineeringHard

One Customer Can See Another Customer's Data

Forward DeployedHard

Code Comprehension

Vector Embedding Normalization Missing Causes Low Similarity Scores

Reported at OpenAIAI EngineeringEasy

Code Comprehension

Conversation history manager fails to truncate old messages properly

Reported at CohereSWE (AI-Era)Medium

Code Comprehension

Customer PII Is Leaking Into the Logs

Forward DeployedMedium

Code Comprehension

Fine-tuned model tokenizer mismatch with deployment environment configuration

Reported at MetaAI EngineeringHard

Code Comprehension

Sliding Window Rate Limiter for Concurrent LLM API Calls

Reported at DatabricksSWE (AI-Era)Medium

Agent Is Slow Because It Calls Tools One at a Time

Forward DeployedMedium

Code Comprehension

Loading more problems…