Learn AI Engineeringin 10 Weeks

Understand the fundamental building blocks of LLMs with tokenization, vectorization and attention.

• Tokenisation, Vectorization, Attention

• Pre-training and post-training

• LLM Evaluations

• End-to-end LLM lifecycle

Learn how LLMs are quantized for fast processing, and how to fine-tune models to meet specific business requirements.

• Fine-tuning - LoRA/QLoRA

• Quantization - FP16, attention optimizations

• When to fine-tune vs. when not to?

• Fine-tuning an SLM for tool use

Learn chunking strategies, data ingestion, reranking, indexing, vector databases, and other techniques for retrieval augmented generation.

• RAG: chunking strategies, data ingestion, reranker, indexer

• Vector Embeddings, Vector Databases

• Search Algorithms: ANN algorithms (HNSW, IVF)

An interactive project where students learn to code a RAG-based application and learn best practices for AI safety.

• Reranking strategies, Query rewriting, HyDE

• Input and output guardrails

• Safety: Prompt injection, Intent classification

• Coding Assignment: Build a RAG chatbot using API calls

Learn what an Agent is, how they are different from plain LLMs, Tool Calling, ReAct pattern, and Agent Orchestration.

• LLM vs Agent vs Multiple Agents

• ReAct pattern

• Prompt Chaining, Orchestration, Routing

• Coding Assignment: Customer support agent

Code an AI Agent with MCP and memory, optimizing agentic flow.

• Context Engineering

• Memory in Agents

• Model Context Protocol

• Multi-Agents

• Coding Assignment: MCP with memory and context optimization

Learn how Evals are used in production AI applications, and best practices for AI development.

• Evals: How to avoid hallucinations with Evals

• LLM as a Judge

• Tradeoffs and design decisions

• Fine-tuning vs Prompting vs RAG

• Project: Build your own LLM Judge

Learn how AI agents are scaled in distributed systems, and the system design of large-scale AI applications.

• Agents at scale

• MCP vs. API wrappers

• Design tradeoffs

• Best practices for agentic system design

Learn how multimodal models are trained with images and video, and the mechanism of diffusion-based models.

• Multimodal models

• CLIP

• Video Models

• CoT, RLHF

Create a production-grade AI project on a topic of your choice.

• Recap important concepts

• Problem selection

• Metrics for evaluation

• Feedback on completed projects