2026 Workshops
Workshops will be held on April 16th, Day 3 of the conference. Take advantage of hands on sessions from industry experts to increase your skills in deploying models to production.
Mastering AI Agents
Hamza Farooq - Founder - Traversaal.ai/ex-Google
This workshop provides a comprehensive understanding of designing and building AI agents from the ground up. Instead of relying on pre-built frameworks like CrewAI or Autogen, participants will learn the core mechanics of agent development to create fully customizable solutions. By the end, attendees will have the tools and knowledge to build robust, scalable, and production-grade AI agents tailored to their needs.
Optimizing Enterprise RAG Systems
Trey Grainger - Author - AI-Powered Search
RAG systems will be a mainstay in every enterprise. Tuning a RAG systems involves deep knowledge of both vector and traditional keyword search, coupled with efficient context management strategies for LLMs. This entire equation becomes more complicated when multiple modalities of data enter the equation.
Hands-On Technical Workshops: Go beyond the theory with deep-dive sessions led by industry pioneers.
Master the full stack of agentic AI—from GPU-level inference to multi-agent orchestration. Workshops take place on the afternoon of Day 2 at 1:00 PM on March 31.
Building an AI-Native Career: How to use AI to Uplevel Yourself Professionally
The way we work is evolving fast — and AI-native professionals are learning how to move from using tools to building workflows. In this session, you’ll explore how agentic CLI tools go beyond coding, how “vibe insights” reduce the distance between data and action, and how ephemeral software can help you solve niche problems quickly. Learn to see the world through “software vision” and develop the mindset needed to stay adaptable, productive, and ahead of the curve in an AI-driven era.
Optimizing LLM Training and Inference Performance on GPUs
Zeyuan (Faradawn) Yang- Technical Marketing Engineer - NVIDIA
This 1.5 hour workshop explores how to optimize GPU performance and reduce operational costs when training and serving large language models. Attendees will learn practical strategies for high-throughput training and low-latency inference, including modern parallelism techniques and disaggregated serving architectures used in production-scale LLM systems.
Workshops take place on the afternoon of Day 2 at 1:00 PM on March 31.
Mastering Agentic Coding & GPUs
Anton Alexander - Sr. GenAI Specialist for NVIDIA - AWS
Mastering Agentic Coding and GPUs is a hands-on, 2-hour workshop focused on building, deploying, and scaling production-ready agentic systems. Learn how to structure agentic coding workflows, ensure reliability and safety, and effectively use GPUs and Kubernetes to run agent-driven workloads from experimentation through production.
Multi Agent Architecture using ADK (Google)
Hamza Farooq - CEO - Traversaal AI (Ex-Google)
In this 45-min workshop, learn how to build collaborative multi-agent systems using Google’s Agent-to-Agent (A2A) protocol, MCP, and the Google Agent Development Kit (ADK). This session shows how agents communicate, share context and tools, and coordinate tasks—bringing everything together to design multi-agent systems that work together on complex problems.
Optimizing Retrieval for Agentic Systems
Trey Grainger - Founder & CEO, Searchkernel | Author, AI-Powered Search | Ex-Lucidworks, Presearch, & CareerBuilder | Adjunct Professor at Furman University
In this 45-min workshop, you’ll learn the core techniques and design patterns behind modern AI-powered retrieval. Since the quality of RAG systems is driven largely by retrieval, we’ll focus on how to design and optimize retrieval for AI and agentic systems, and introduce agentic search, where agents coordinate retrieval through tool calls and relevance feedback loops.
Context Engineering with Redis and LangChain
Robert Shelton - Applied AI Engineering Manager - Redis
Design scalable AI agents by mastering context engineering — the discipline of structuring memory, retrieval, and reasoning workflows so LLMs behave reliably in production. This workshop explores how Redis and LangChain enable high-performance agent systems through semantic caching, vector search, and intelligent context management.
Agentic Engineering for End-to-end Product Ownership
Brendan O'Leary & Brain Turcotte - Developer Relations - Kilo Code
[1 hour] The first wave of AI coding assistants gave us unreliable code generators or glorified autocomplete. Now we're witnessing a fundamental shift to agentic engineering—but many developers are stuck in "vibe coding" mode, accepting whatever the AI produces without the skills to evaluate, direct, or collaborate effectively. This workshop bridges that gap, teaching you to move to owning a complete product lifecycle with a new approach to agentic engineering.
Mastering Agentic Coding & GPUs
Anton Alexander - Sr. GenAI Specialist for NVIDIA - AWS
Mastering Agentic Coding and GPUs is a hands-on, 2-hour workshop focused on building, deploying, and scaling production-ready agentic systems. Learn how to structure agentic coding workflows, ensure reliability and safety, and effectively use GPUs and Kubernetes to run agent-driven workloads from experimentation through production.
Multi Agent Architecture using ADK (Google)
Hamza Farooq - CEO - Traversaal AI (Ex-Google)
In this 2-hour workshop, learn how to build collaborative multi-agent systems using Google’s Agent-to-Agent (A2A) protocol, MCP, and the Google Agent Development Kit (ADK). This session shows how agents communicate, share context and tools, and coordinate tasks—bringing everything together to design multi-agent systems that work together on complex problems.
Workshops take place on the afternoon of Day 2 at 1:00 PM on March 31. Join hands-on sessions led by industry experts to build practical skills for deploying and scaling AI systems in production
Optimizing Retrieval for Agentic Systems
Trey Grainger - Founder & CEO, Searchkernel | Author, AI-Powered Search | Ex-Lucidworks, Presearch, & CareerBuilder | Adjunct Professor at Furman University
In this 2-hour workshop, you’ll learn the core techniques and design patterns behind modern AI-powered retrieval. Since the quality of RAG systems is driven largely by retrieval, we’ll focus on how to design and optimize retrieval for AI and agentic systems, and introduce agentic search, where agents coordinate retrieval through tool calls and relevance feedback loops.
Optimizing LLM Training and Inference Performance on GPUs
Zeyuan (Faradawn) Yang- Technical Marketing Engineer - NVIDIA
This workshop explores how to optimize GPU performance and reduce operational costs when training and serving large language models. Attendees will learn practical strategies for high-throughput training and low-latency inference, including modern parallelism techniques and disaggregated serving architectures used in production-scale LLM systems.