Top 12
Prep plan
Updated weekly · Last refresh Oct 17

Commonwealth Bank of Australia AI Engineer Interview Questions

The questions to prepare for a Commonwealth Bank of Australia AI Engineer interview. Questions from real interview reports rank first. Updated daily.

12questions
~2htotal time
Track your progressSign up free to work through all 12 questions and resume where you left off.
Start practicing free →
1
Generative AI & LLMsStart here. 5 questions · ~47 min
Embeddings and Vector SearchHard

Explain how to build, evaluate, scale, and secure embedding-based document retrieval for a production RAG system.

Vector SearchRAGscalabilityCommonwealth Bank of Australia
LLM Serving for Latency and ThroughputHard

Design a production LLM serving system that balances latency, throughput, cost, reliability, and safe degradation.

latencyllm deploymentinference optimizationCommonwealth Bank of Australia
Multi-Agent System ArchitectureHard

Design a safe, observable multi-agent architecture for complex workflows while controlling latency, cost, hallucination, and prompt injection.

multi-agent systemstool useworkflowCommonwealth Bank of Australia
More Generative AI & LLMs questions with a free account
2
More topics7 questions · ~66 min
Cosine Similarity From ScratchMedium
Practice

Compute cosine similarity for equal-length high-dimensional vectors using dot products and Euclidean norms.

function implementationArraysArray ManipulationCommonwealth Bank of Australia
Distributed Embedding and Vector SearchHard

Design a distributed service for generating embeddings and searching millions of frequently changing documents.

Vector Searchdistributed systemsinference latencyCommonwealth Bank of Australia
Balancing Accuracy and ExplainabilityHard

Compare interpretable and high-performing models for financial decisions while preserving auditability, fairness, and regulatory defensibility.

model selectionTrade-offsinterpretabilityCommonwealth Bank of Australia
Model Drift ReliabilityHard

Design a production monitoring and retraining strategy for detecting model drift and preserving long-term prediction reliability.

production systemsdata driftmodel validationCommonwealth Bank of Australia
High-Concurrency LLM ServingHard

Design a low-latency, high-concurrency LLM serving layer with effective prompt, response, and KV-cache strategies.

high-frequency requestsinference latencyml inferenceCommonwealth Bank of Australia
More 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
The finish line: interview-readyComplete all 12 questions to finish this plan.