AI Industry Training and Hackathon

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
 

AI Engineering Bootcamp (3 Days)

Day 1: Building with AI

Session 1: Where the Future Economy is Headed with Software 2.0
Duration: 2 hours | Format: Presentation & Discussion

• Creating value in the future economy: electricity + compute + developers = revenue
• Evolution of software architectures: from monoliths to AI agents
• The age of personal software and the future of SaaS
• RAG techniques and limitations of LLMs
• Agentic applications and why they matter
• The economics of inference: cost, latency and throughput
• Edge AI and the on-prem trend
• Gigabyte AI developer hardware introduction

Session 2: Hands-On Lab - Building with AI
Duration: 6 hours | Format: Lab-based

Requirements

• Bring your own laptop
• WSL and Ubuntu required
• 1-month Claude voucher provided

Greenfield Software Development (4 hours)

• Prompt Engineering Fundamentals
• Building skills and skill composability
• Context Engineering & Memory (Vector RAG, Graph RAG)
• Connecting to agents using MCP servers
• Planning and designing
• Testing and iteration

Legacy Code & Migration (2 hours)

• Re-engineering and migrating legacy codebases
• Patterns, methods and workflows
• Architectures for AI-assisted development
• Reducing token usage through context engineering
• AI-augmented developer workflows
• Human-in-the-loop reviews and QA
• Debugging AI applications with LangSmith

Day 2: Building AI - AI Engineering Foundations
Duration: 8 hours

Session 3: Infrastructure & Models (3 hours)

• GB10 (Gigabyte AI Top Atom) clustering
• Environment setup and dependencies
• Hosting foundation models
• Short-term memory systems

Session 4: Evaluation & Light Customization of LLMs (2 hours)

• LLM evaluation fundamentals
• Benchmark testing using GSM8K
• PEFT and LoRA fine-tuning
• NVIDIA NeMo Framework, Evaluator and Customizer
• NVIDIA Inference Microservices (NIMs)
• MLflow experiment tracking

Session 5: Agents (3 hours)

• LangChain Foundations (Python)
• Building simple agents
• Model Context Protocol (MCP)
• Multi-agent systems
• Setting up coding agents
• Multimodal agents
• VLMs and VLQA
• OpenClaw and NemoClaw setup
• Building coding and automation agents

Day 3: Hackathon
Duration: 8 hours

Logistics

• 15 AI Top Atom workstations provided by Gigabyte
• Monitors, keyboards and mice supplied
• 9 teams of 4-5 participants

Competition Format

• Part 1 (30%): AI model and LLM evaluations across Data Science, LLMs and Computer Vision.
• Part 2 (30%): Build Claw bots and task-oriented agents.
• Part 3 (40%): Agent vs Agent competition in a round-robin format.

Further Details

For further information about the course, please contact Alan Hsiao (a.hsiao@unsw.edu.au).

To register your interest, visit: 2026 AI Industry Training & Hackathon Registration