top of page
image (84) (1).png

NVIDIA Full-Day Technical Workshops

Exclusive Pre-Conference Sessions at IIT2026 Global Conference

Building Agentic AI Applications with LLMs 
(Offered by NVIDIA)

AI agents are moving beyond chat. Modern agents can reason, research, use tools, and execute complex objectives at scale. This hands-on workshop teaches you how to design and build agentic AI systems that perform deep reasoning, structured decision-making, software tool calling, and concurrent task execution.

There are two workshops offered by NVIDIA 

​Building Agentic AI Applications with LLMs 

Date: Wednesday, April 22, 2026
Time: 8:00 AM to 5:00 PM
Location: IIT2026 global conference 

Rapid Application Development with LLMs

Date: Wednesday, April 22, 2026
Time: 8:00 AM to 6:00 PM
Location: IIT2026 global conference 

Exclusive Pre-Conference Sessions at IIT2026 Global Conference

You will learn how to architect agents that retrieve and refine information, route queries intelligently, and operate reliably using orchestration frameworks like LangGraph and strong software engineering practices.

Event details 

Date: Wednesday, April 22, 2026
Time: 8:00 AM to 5:00 PM
Location: IIT2026 global conference 


Price: $199 per attendee (conference attendees only)
Capacity: Capped at 150 attendees


Lunch: Included

image (85).png

Learning Outcomes

704786cccd57663772bb52a4e531352315ba4073 (1).png

Generate structured outputs for reliable API and function calling

704786cccd57663772bb52a4e531352315ba4073 (1).png

​Implement retrieval mechanisms including vector search and knowledge graphs

704786cccd57663772bb52a4e531352315ba4073 (1).png

​Design and orchestrate multi-agent systems using frameworks like LangGraph

704786cccd57663772bb52a4e531352315ba4073 (1).png

​Build scalable, multi-tenant agent APIs for real-world use

704786cccd57663772bb52a4e531352315ba4073 (1).png

Understand the strengths and limitations of LLMs and why agent-based systems are needed

Core Topics

​From LLM fundamentals to multi-agent orchestration, this workshop covers structured outputs, retrieval systems, concurrency, and scalable agent deployment.
176e0a_3fbb7f8f77324fb382bdcab06fefdc4fmv2 1.png

LLM fundamentals and agent abstractions

​Structured outputs and schema 
enforcement

Retrieval-augmented generation and environmental tooling

Multi-agent systems, concurrency, and orchestration

Real-time constraints, data flywheels, and scaling considerations

Final assessment: deploy an agent that coordinates multiple retrieval tasks and returns structured research outputs

176e0a_3fbb7f8f77324fb382bdcab06fefdc4fmv2 2.png
A structured, hands-on deep dive into LLM foundations, agent and application architectures, retrieval, orchestration, multimodality, and scalable production deployment.

Rapid Application Development with Large Language Models

Large language models are transforming how applications are built, enabling faster development, lower operational costs, and new AI-driven user experiences. This workshop provides an end-to-end, hands-on introduction to building production-ready LLM applications using open-source models, modern pipelines, and orchestration frameworks.
Participants will learn how to develop scalable, safe, and effective LLM-powered applications across text, multimodal data, and agentic workflows.

Offered by NVIDIA

Date: Wednesday, April 22, 2026
Time: 8:00 AM to 6:00 PM
Duration: Full-day workshop

Price: $199 per attendee (conference attendees only)
Capacity: Capped at 150 attendees


Lunch: Included

image (87).png

Learning Outcomes

704786cccd57663772bb52a4e531352315ba4073 (1).png

​Apply encoder models for embeddings, semantic search, classification, and question answering


704786cccd57663772bb52a4e531352315ba4073 (1).png

Use decoder and encoder-decoder models for text generation and sequence tasks

704786cccd57663772bb52a4e531352315ba4073 (1).png

Build multimodal applications using text, images, and audio

704786cccd57663772bb52a4e531352315ba4073 (1).png

Orchestrate LLM pipelines and agentic workflows using LangChain

704786cccd57663772bb52a4e531352315ba4073 (1).png

Work with pretrained models from the HuggingFace ecosystem using Transformers

Core Topics

​From LLM fundamentals to multi-agent orchestration, this workshop covers structured outputs, retrieval systems, concurrency, and scalable agent deployment.
176e0a_3fbb7f8f77324fb382bdcab06fefdc4fmv2 1.png

Transformer fundamentals and LLM foundations

Task-specific pipelines and lightweight model usage

Sequence-to-sequence and generative architectures


Multimodal systems including text, vision, and audio


Scaling LLM inference and deployment strategies


Orchestration and agentic workflows

Final assessment: build an LLM application integrating text generation, multimodal learning, and orchestration

176e0a_3fbb7f8f77324fb382bdcab06fefdc4fmv2 2.png

Important notes

  • Both workshops are exclusive to IIT2026 conference attendees

  • Seats are limited and expected to fill quickly

  • Each workshop requires a separate registration
bottom of page