Top 20
Prep plan
~3h total · Updated weekly · Last refresh Aug 9

Remitly AI Engineer Interview Questions

The questions to prepare for a Remitly AI Engineer interview. Questions from real interview reports rank first. Updated weekly.

Choose Between RAG and Fine-TuningEasy

Compare RAG and fine-tuning, and decide when each is the better fit for an LLM product.

Remitly
Fix Hallucinations in RAG Answers
Easy

Reduce hallucinations in a RAG system even when retrieval is already correct, using grounding, verification, and evaluation.

Remitly
Evaluate an LLM System
Medium

Explain how to evaluate a generative model using offline and online methods, with attention to hallucination, product metrics, and experiment design.

HallucinationPrompt EngineeringLLM Evaluation
Remitly
More Generative AI & LLMs questions with a free account
More Behavioral & Leadership questions with a free account
Design an LLM Serving PlatformHard

Design an LLM serving system that balances latency, cost, scalability, and safety for production traffic.

Cold StartFeature StoreModel Serving
Remitly
Cache Layer for LLM Responses
Medium

Tests your ability to design caching strategies that preserve correctness while improving latency and reducing LLM spend.

latencycachingModel Serving
Remitly
More System Design questions with a free account

Sign up to see every question

Create a free account to unlock this list and practice real interview questions.

Get my prep plan
Detect Rolling Window Anomalies
Medium

Tests your skills in streaming analytics and anomaly detection logic under time-window constraints.

Stream ProcessingSliding Windowanomaly detection
Remitly
Efficient Transaction Record Store
Medium

Tests your understanding of data structures and algorithmic trade-offs for dynamic transaction datasets.

Hash TablesData Structuresoop
Remitly
More Coding questions with a free account
Parse and Tokenize Feedback Data
Medium

Tests your data preprocessing skills for NLP pipelines, including cleaning and tokenization for model training or inference.

data cleaningcustomer feedbackTokenization
Remitly