A 30-session, hands-on program that takes students from AI system fundamentals to designing, building, evaluating, improving, and deploying AI applications — across foundation models, context engineering, RAG, fine-tuning, agentic systems, and modern AI infrastructure.
Understand how AI systems are structured, break problems into models, context, knowledge, tools, and applications, and design system architectures before building.
Work with open-weight and proprietary foundation models, compare models based on capability, quality, latency, and cost, integrate LLM APIs, and build multi-model AI applications.
Design system instructions, structured outputs, memory, and context pipelines, then connect AI systems to external knowledge through RAG, embeddings, vector search, hybrid retrieval, reranking, and grounding.
Build evaluation datasets and test suites, measure RAG and LLM performance, use RAGAS and DeepEval, apply LLM-as-a-Judge techniques, and use evaluation results to improve system performance.
Adapt models using LoRA and QLoRA, build AI agent workflows with tool use and MCP, apply security and guardrails, deploy AI applications publicly, manage projects with GitHub, and present a portfolio project.
Fewer than 3 in 100 applicants are selected.
Foundations and CS Specialist
"You can't build AI you don't understand. My job is to make the maths underneath it feel obvious - not intimidating."
Programming & Applied AI Specialist
"Students learn AI fastest when they're building something real with it. We start writing code on day one."
Programming & AI Engineering Specialist
"Real industry experience changes how you teach. I show students how AI is actually built, not just how it's described."
In the final three sessions, they design an end-to-end AI system, integrate foundation models and retrieval, evaluate and improve performance, deploy the application, and present it live as a portfolio project.
30 private 1-on-1 sessions with an IIT graduate mentor.
for the full 30-session course
$33 per 1-on-1 session · 30 sessions total
