2026 AI Industry Training & Hackathon

29 - 31 July 2026

Register your interest

Contact us

Event Banner - AI Industry Training and Hackathon

Format

In-person

Duration

3 days

Venue

91ɫ��Ƭ Sydney CBD campus, Level 4/210 George Street, Sydney

Course fee

$1500

Next available date

29 - 31 July 2026

Course overview

This program is 3 day industry training and hackathon designed for software engineers and technical professionals who wants to build, deploy, and compete with real AI systems. It is suited to:

Software engineers and developers building or integrating AI into their products
Technical professionals working with large language models, agents, and AI infrastructure
Engineers looking to gain hands-on experience with model evaluation, fine-tuning, and agentic frameworks
Developers interested in the latest tooling from NVIDIA, LangChain, and the open-source AI ecosystem
Participants should have a working knowledge of Python and be comfortable in a Linux/command-line environment. Capacity is limited to 40 attendees

Trainers from NVIDIA, Anthropic and LangChain

Intended audience
Schedule
Learning objectives
Speakers and facilitators
Course outline

This program is designed for software engineers and technical professionals who want to build, deploy, and compete with real AI systems. It is suited to:

Software engineers and developers building or integrating AI into their products
Technical professionals working with large language models, agents, and AI infrastructure
Engineers looking to gain hands-on experience with model evaluation, fine-tuning, and agentic frameworks
Developers interested in the latest tooling from NVIDIA, LangChain, and the open-source AI ecosystem

Participants should have a working knowledge of Python and be comfortable in a Linux/command-line environment. Capacity is limited to 40 attendees

This is a 3 Day course starting from 29 - 31 July 2026.

Day 1 Breakdown (8 hours)

Session 1 (2 hrs): Where the Future Economy is Headed with Software 2.0 — presentation & discussion
Session 2 (6 hrs): Hands-On Lab — Building with AI, Transitioning to No-Manual Coding

Day 2 Breakdown (8 hours)

Session 3 (3 hrs): Infrastructure & Models
Session 4 (2 hrs): Evaluation & Light Customisation of LLMs — delivered by NVIDIA
Session 5 (3 hrs): Agents — delivered by LangChain

Day 3 Breakdown (8 hours)

Part 1 (30%): AI model/LLM evaluation challenges across data science, LLM, and Computer Vision
Part 2 (30%): Build Claw bots/agents to complete assigned tasks
Part 3 (40%): Agent vs Agent round-robin competition

By the end of this program, participants will be able to:

Configure and utilise bare-metal AI hardware to self-host and run open-source large language models
Set up and manage AI infrastructure including GB10 clustering and foundational model hosting
Evaluate large language models using industry benchmark frameworks such as GSM8K
Apply parameter-efficient fine-tuning (PEFT) with Low-Rank Adaptation (LoRA) using the NVIDIA NeMo framework
Deploy NVIDIA Inference Microservices (NIMs) and track experiments using MLflow
Build simple and multi-agent systems using LangChain and the Model Context Protocol (MCP)
Work with multi-modal agents including Vision Language Models (VLMs)
Design, build, and deploy a competitive AI agent in a live hackathon environment

Trainer from NVIDIA
Trainer from Anthropic
Trainer from LangChain

Session 1 — Where the Future Economy is Headed with Software 2.0 (2 hours)

Creating value in the future economy: electricity + compute + developers = revenue
Evolution of software architectures — from monoliths to AI Agents
The death of SaaS and the age of personal software
The path to reasoning — RAG techniques and LLM limitations
Agentic applications — what they are and why they matter
The economics of inference — cost per token, latency vs. throughput tradeoffs
Edge AI and the on-prem trend
Gigabyte AI developer hardware introduction

Session 2 — Hands-On Lab: Building with AI (6 hours)

Greenfield Software Development (4 hours)

Prompt Engineering Fundamentals
Building skills and skill composability
Context Engineering and memory (Vector RAG, Graph RAG) — Obsidian & Graphify
Connecting to agents using MCP servers
Planning, designing, testing & iteration

Legacy Code & Migration (2 hours)

Re-engineering and migrating legacy codebases (clean-room re-implementation)
Architectures and patterns for AI-assisted development
Reducing token usage through context engineering
Ways of working: the AI-augmented developer workflow
Human in the loop, code reviews, and QA
Debugging AI apps in production

Day 2: AI Engineering Foundations

Session 3 — Infrastructure & Models (3 hours)

GB10 (Gigabyte AI Top Atom) clustering setup
Environment configuration and dependencies
Hosting foundational models and managing short-term memory

Session 4 — Evaluation & Light Customisation of LLMs (2 hours)
Delivered by NVIDIA.

LLM Evaluation Fundamentals
Running benchmark evaluation using GSM8K
Parameter-Efficient Fine-Tuning (PEFT) with Low-Rank Adaptation (LoRA)
NVIDIA NeMo Framework, NeMo Evaluator, and NeMo Customizer
NVIDIA Inference Microservices (NIMs)
MLflow for Experiment Tracking

Session 5 — Agents (3 hours)
LangChain Foundations (Python) — delivered by LangChain

Building simple agents in Python
Model Context Protocol (MCP): what it is, building an MCP server, connecting to third-party MCP servers
Multi-agent protocols
Setting up a coding agent

Multi-modal Agents

Vision Language Models (VLMs) and Visual LLM Question Answering (VLQA)

Openclaw

Openclaw/Nemoclaw environment setup
Configuring your own coding agent (Clawcode)
Claw automation tutorial — e.g. email automation agent

Day 3: Hackathon

Format & Logistics

7 teams of 4–5 participants
Equipment: 15 × AI Top Atoms, monitors, mouse and keyboard supplied by Gigabyte
Adjudicated by leading academics from 91ɫ��Ƭ and Macquarie University, and industry experts from NVIDIA and Cognitivo

Competition Structure

Part 1 (30%): AI model/LLM evaluations across data science, LLM, and Computer Vision categories
Part 2 (30%): Teams build Claw bots/agents to complete defined tasks
Part 3 (40%): Agent vs Agent — teams build an agent to compete in a round-robin format against other teams