About This Course
In a world where efficiency, uptime, and data-driven decisions define manufacturing success, Large Language Models (LLMs) are no longer just experimental - they're necessary operational tools. This 5-day course is designed for engineers, technologists, and AI teams aiming to apply LLMs in real manufacturing workflows.
Participants will go beyond the basics and develop advanced skills in LLM architecture, RAG pipelines, fine-tuning with factory data, agentic decision workflows, and multimodal AI applications (e.g., combining machine logs and visual inspections).
The course culminates in a capstone project, where learners prototype an AI assistant customized for their facility - ranging from predictive maintenance bots to procurement chat interfaces and factory floor knowledge agents.
Learning Objectives
By the end of the training, participants will be able to:
- Understand and apply advanced LLM techniques in manufacturing environments
- Build Retrieval-Augmented Generation (RAG) systems tailored to factory knowledge
- Optimize prompt engineering for real-world industrial tasks and SOPs
- Fine-tune LLMs using logs, technical documents, and shop floor annotations
- Implement LangChain agent workflows for complex, multi-step factory reasoning
- Integrate LLMs with images, tables, or sensor data for context-aware outputs
- Choose and deploy models using cloud APIs, quantized local runtimes, or edge devices
- Evaluate model performance, apply safety filters, and prevent hallucinations
- Design and deliver a working AI prototype with direct manufacturing value
- Make strategic decisions about AI adoption in cost-sensitive, high-precision environments
Prerequisites
- Basic Python Programming: Understanding of Python is essential, though the course includes a primer for those with less experience.
- Fundamental AI Concepts: A general grasp of AI and machine learning concepts is helpful, though not mandatory as foundational lessons are included.
- Interest in AI Development: A keen interest in learning and applying AI technologies, particularly LLMs.
- Problem-Solving Skills: Ability to think critically about how to apply LLMs to solve real- world problems.
- Willingness to collaborate in project-based work during the final 2 days
Target Audience
- Manufacturing Engineers exploring automation or data-assisted decision-making
- Digital Transformation Leads or Smart Factory Architects
- Maintenance Engineers seeking intelligent fault diagnosis systems
- Process or Quality Engineers wanting to embed AI into reporting, inspections, and analysis
- Software Developers building LLM-powered tools or bots for production sites
- R&D and Innovation Teams tasked with AI strategy or productivity pilots in factories
Training Outline
- AI Fluency: Intro to Generative AI & LLMs
- Foundation of LLM Architecture
- Prompt Engineering for Manufacturing Tasks
- Using APIs to Access Commercial LLMs
- Retrieval-Augmented Generation (RAG) for Manufacturing Docs
- Embedding Models and Vector DBs
- Fine-Tuning & LoRA for Industrial Use Cases
- Building Agentic Workflow with LangChain or LlamaIndex
- Evaluating & Testing LLMs for Industry
- Capstone Project: Deploying a Prototype in Manufacturing