AI Engineering Interview Questions — Practice Library | Velocode

This week's hardest·Reported at MetaNext Word Prediction System Architecture Design→

200+ problems

Problem

Tags

Type

RAG Evaluation Pipeline Failing to Filter Low Quality Responses

Reported at GoogleSWE (AI-Era)Hard

Code Comprehension

Streaming Clickstream Lakehouse: Storage, Compaction, Queries, Schema Evolution

Reported at DatabricksData EngineeringHard

Model Compression — Hitting a 50ms Latency Target

ML EngineeringHard

Automated Citation Fabrication Detection and Remediation Pipeline Architecture

Reported at PerplexityAI EngineeringMedium

Red-team harness for automated prompt-injection bypass discovery

Reported at OpenAIAI SecurityHard

LLM Summarizer Producing Hallucinated Content At High Failure Rate

SWE (AI-Era)Medium

Code Comprehension

LLM retry logic causes infinite loops on malformed API responses

Reported at MetaSWE (AI-Era)Easy

Code Comprehension

AI Agent Prompt Injection Attack Via Support Ticket Content

Reported at AnthropicSWE (AI-Era)Hard

Code Comprehension

Semantic Search Returns Identical Results Regardless Input Query

SWE (AI-Era)Easy

Code Comprehension

Product Daily Revenue Rolling 30-Day Percentile Rank Calculation

Reported at AmazonData EngineeringMedium

Silent data drift detection in production ML pipeline accuracy collapse

Reported at DatabricksSWE (AI-Era)Medium

Code Comprehension

Vector Embedding Space Mismatch Between Query And Document Processing

SWE (AI-Era)Easy

Code Comprehension

RAG Chatbot Fails to Answer Despite Successfully Retrieving Relevant Documents

Reported at GoogleSWE (AI-Era)Easy

Code Comprehension

Model Benchmarking: Metrics, Traffic Split, and Rollout Strategy

Reported at NetflixML EngineeringMedium

Deployment Patterns — Canary Rollout for a New Recommendation Model

ML EngineeringMedium

Delta Lake Time Travel: Querying Historical Table Versions

Reported at DatabricksData EngineeringHard

RAG evaluation metrics masking real-world answer quality failures

Reported at AnthropicSWE (AI-Era)Medium

Code Comprehension

A/B Testing — Analysing ML Model Experiment Results

ML EngineeringHard

Schema evolution resilience: versioning, compatibility layers, registry patterns

Reported at GoogleData EngineeringHard

Spark Join OOM: Check broadcast threshold and shuffle partition configuration

Reported at DatabricksData EngineeringHard

LLM Summarization Tool Cuts Off Mid-Sentence Completion Issue

SWE (AI-Era)Easy

Code Comprehension

Building Customer Support Agent Evaluation Harness: Metrics Design and Contamination Prevention

Reported at AnthropicAI EngineeringMedium

LLM Pipeline PII Redaction Architecture Design and Compliance Strategy

Reported at JP Morgan ChaseAI SecurityMedium

Model Serving — Batch vs Real-Time Architecture Decision

ML EngineeringMedium

Loading more problems…