These are GenAI questions of the kind Infosys actually asks — the patterns that keep coming back in Infosys's GenAI and AI-project interview rounds, where the focus is on applying LLMs sensibly for clients rather than research depth. My advice: treat this page as a mock interview. Say every answer out loud before revealing it — GenAI rounds are conversations, not written tests. If an answer surprises you, the lesson behind it is linked at the bottom.
Infosys GenAI concept questions
Why is RAG usually preferred over fine-tuning for enterprise knowledge chatbots? Give at least three reasons.
Asked in
Why is LLM API pricing based on tokens rather than requests or characters, and what practical habits does that create for developers?
Asked in
What does 'Responsible AI' mean in practice for a GenAI application? Name the main pillars.
Asked in
Infosys GenAI applied & hands-on questions
Write a few-shot prompt that routes IT helpdesk tickets into exactly one of: HARDWARE, SOFTWARE, ACCESS, OTHER. Include three examples, then the target ticket: "I can't log into the VPN since yesterday, keeps saying invalid credentials."
Asked in
How to use this page: Infosys rarely asks a question you've never seen — they ask standard GenAI concepts and then push one level deeper ("why?", "what would you do if..."). Master the concept in the GenAI course lessons, and the follow-up stops being scary.
Keep practising: How LLMs Work, Prompting Basics, RAG and Fine-tuning vs RAG cover what most Infosys GenAI rounds test — and the Infosys exam guide covers the rest of their selection process.