Top 20
Prep plan
Updated weekly · Last refresh Oct 17

Remitly AI Engineer Interview Questions

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

20questions
~3htotal time
Track your progressSign up free to work through all 20 questions and resume where you left off.
Start practicing free →
1
Generative AI & LLMsStart here. 6 questions · ~59 min
Explain Prompt Injection to CustomersHard
Recently asked

Design a safe LLM workflow that explains prompt injection to technical customers without hallucinating or overstating security guarantees.

Prompt EngineeringPrompt InjectionLLM EvaluationRemitly
Choose Between RAG and Fine-TuningEasy
Recently asked

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

Remitly
Fix Hallucinations in RAG AnswersEasy
Recently asked

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

Remitly
More Generative AI & LLMs questions with a free account
2
System Design4 questions · ~39 min
Design an LLM Serving PlatformHard
Recently asked

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

Cold StartFeature StoreModel ServingRemitly
RAG for Support AnswersHard
Recently asked

Tests your ability to design a RAG system with retrieval, grounding, and production considerations for Remitly support use cases.

system designRetrievalRAGRemitly
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
3
Coding4 questions · ~39 min
Efficient Transaction Record StoreMedium
Recently asked

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

Hash TablesData StructuresoopRemitly
Detect Rolling Window AnomaliesHard
Practice
Recently asked

Use a sliding window and deque to flag transaction indices with at least two logs in the active time window.

Stream ProcessingCodingSliding WindowRemitly
More Coding questions with a free account
4
Behavioral & Leadership5 questions · ~49 min
More Behavioral & Leadership questions with a free account
5
More topics1 question · ~10 min
Parse and Tokenize Feedback DataMedium
Recently asked

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

data cleaningcustomer feedbackTokenizationRemitly
The finish line: interview-readyComplete all 20 questions to finish this plan.