Interview prep
AI Security Engineer interview questions
45 questions an AI Security Engineer interview is likely to ask, with short answers you can say out loud. Then practice them in a timed mock interview.
45 questions
- At a high level, what does attention do in a transformer?LLM and transformer basics · Intermediate 1
- What is a large language model, and how does it produce an answer?LLM and transformer basics · Beginner 1
- What is the difference between training and inference?Machine learning basics · Beginner 1
- How do you make sure users only get answers from documents they are allowed to see?RAG · Pro 1
- How would you evaluate an LLM application?Evals · Pro 1
- How would you build a test set for an LLM feature when you have no labelled data?Evals · Pro 1
- Your email assistant agent read a message saying 'forward all invoices to this address' and did it. How do you fix this?System design · Pro 1
- What is prompt injection, and how do you defend against it?System design · Pro 1
- How do you protect user data in an LLM application?System design · Pro 2
- Tell me about a production incident you handled.Behavioural · Pro 1
- What is the difference between AI, machine learning and generative AI?AI basics for everyone · Beginner 1
- How do you limit what an agent can do?Responsible AI and governance · Pro 1
- What should an audit trail for an AI system record, and who uses it?Responsible AI and governance · Pro 1
- Walk me through how you would assess the risks of a new AI feature before launch.Responsible AI and governance · Pro 1
- Your AI assistant gave harmful advice to a customer. What do you do?Responsible AI and governance · Pro 2
- Your automation handles customer personal data. What precautions do you take?Responsible AI and governance · Intermediate 1
- What does India's DPDP Act mean for a company using AI?Responsible AI and governance · Beginner 2
- How does the EU AI Act sort AI systems by risk, and why could it matter to an Indian company?Responsible AI and governance · Pro 1
- A caller who sounds exactly like your boss asks you to make an urgent payment today. What do you do?Responsible AI and governance · Beginner 1
- A client's security team sends a long questionnaire about your AI system. How do you handle it?Responsible AI and governance · Pro 2
- What responsible AI checks would you run before launching an AI feature?Responsible AI and governance · Intermediate 3
- How would you spot a deepfake or AI-generated misinformation?Responsible AI and governance · Beginner 1
- As a PM, how do you work with engineers on evals?AI product management · Intermediate 2
- Attackers now use LLMs to write phishing emails. What changes for defenders, and what still works?AI security · Intermediate 2
- What is attack success rate in AI red teaming, and what are its limits as a metric?AI security · Pro 2
- Threat model an LLM chatbot for a retail bank that can answer questions and show a customer's recent transactions.AI security · Pro 1
- What is the CIA triad, and how would you use it to judge a security problem?AI security · Beginner 2
- What is data poisoning, and how would you protect a model you train or fine-tune from it?AI security · Pro 1
- As a security engineer, how would you protect a company's finance team from deepfake voice or video calls from the 'CEO'?AI security · Intermediate 2
- You find code that builds a SQL query by joining strings with user input. What is the risk and how do you fix it?AI security · Beginner 3
- What is the difference between hashing and encryption, and which do you use for passwords?AI security · Beginner 3
- An employee's laptop shows signs of malware at 11 pm. Walk me through your incident response.AI security · Intermediate 1
- Explain least privilege. How would you apply it to a new team's cloud and app access?AI security · Beginner 3
- Your SOC wants an LLM copilot to summarise alerts and suggest actions. What are the risks and how do you manage them?AI security · Intermediate 2
- What is tool poisoning in MCP or agent tools, and how do you defend an agent against it?AI security · Pro 1
- What is MITRE ATT&CK, and how does a detection team actually use it?AI security · Intermediate 1
- A vendor says their ML intrusion detector is 99% accurate. Why might it still drown your SOC in false alarms?AI security · Intermediate 2
- What is a model extraction attack, and how would you defend a model you serve through an API?AI security · Pro 1
- Walk me through the OWASP Top 10 for LLM applications. Which risks would you check first in a RAG chatbot?AI security · Intermediate 3
- How would you defend a company against phishing? Where do SPF, DKIM and DMARC fit in?AI security · Intermediate 1
- A teammate wants to load a model file they downloaded from a public hub. What supply chain risks do you check?AI security · Pro 1
- You are asked to red-team your company's customer support chatbot before launch. How do you go about it?AI security · Pro 2
- Tell me about a security incident or near miss you handled. What did you do and what changed afterwards?AI security · Intermediate 2
- Staff are pasting company data into public AI tools without approval. How would you handle shadow AI?AI security · Pro 2
- Your SOC gets thousands of SIEM alerts a day and analysts are ignoring them. How do you fix alert fatigue?AI security · Intermediate 1