Generative AI Working With Large Language Models

This foundational course teaches practical techniques to work with LLMs including prompt engineering, retrieval-augmented generation, evaluation metrics, and safety guardrails. You’ll learn how to design prompts for reliable outputs, build retrieval pipelines using embeddings, evaluate model outputs with quantitative and qualitative metrics, and implement monitoring for hallucination and bias. The course is oriented at engineers and practitioners building production systems around LLMs.

• Skills you’ll learn: prompt engineering, RAG pipelines, embeddings, evaluation metrics, safety monitoring.

Certificate: Certificate of completion provided upon finishing the course.

Requirements

• Familiarity with LLM concepts and compute or API access.

Who this course is for

• Engineers; ML practitioners; researchers.

Benefits

• Apply prompting best practices; use evaluation metrics; design RAG architectures; implement safety guardrails.