Local LLM–Based AI Technical Training — Internal AI That Keeps Your Data Inside the Company
Work with materials you can’t upload to cloud AI, using AI on company PCs and servers
A hands-on Local LLM course for companies that work with data they cannot upload to external cloud AI, such as test and measurement data, design files and customer technical documents. You run open models (Gemma, Qwen and others) directly on in-house PCs or servers to build an AI environment where data never leaves the company, then apply it to real work such as report drafts, measurement summaries and technical document translation. You also practice RAG for connecting internal documents and Python API integration, all in a single day, and map out an adoption plan that fits your company. Instructor Seongil Kim holds a master’s degree in mechanical engineering from KAIST and led noise-related R&D as a principal researcher at Samsung Electronics, so sessions are taught in the everyday language of engineers. For the hands-on environment, choose what suits your company: run models directly on participants’ laptops, or connect to an in-house server or a Mac mini the instructor brings.
💻 Start learning this topic with an online course →Who is this course for?
An engineer by background, with a bachelor’s and master’s in Mechanical Engineering from KAIST, he worked as a Principal Researcher at Samsung Electronics on noise-related R&D. He is now CEO of Bizunication and a TechCore instructor for the Ministry of Science and ICT, teaching AI automation and AX training.
What will you learn?
- Install and run open models on company PCs and servers, and understand an AI environment where data never leaves your organization
- Apply a Local LLM to report drafts, measurement result summaries, and technical document translation, and build the habit of verifying numerical and unit errors
- Practice connecting internal documents and software through RAG and API integration, and define your company’s adoption roadmap
Curriculum
- In-house AI from a data security perspective
- Cloud AI vs. Local LLM
- Open model landscape (Gemma, Qwen, etc.)
- Internal AI Server Architecture
- Installing Ollama and LM Studio
- Choosing a small model and quantizing it
- (Server setup) Ollama server · Open WebUI · network access
- Drafting reports
- Summarizing measurement results
- Translating English technical documents
- Principles of prompt writing
- Verifying results
- Checking numbers and units for errors
- Comparing quality by model size
- RAG architecture
- Document chunking and embedding
- Connecting document folders and shared storage
- Q&A on sample documents
- Checking answer sources
- Ollama API
- Python Integration
- Automating report generation
- Integration with In-House Software
- Scope of personal PC use
- Server Sizing
- Access and permission management
- Phased adoption plan
- Q&A
Tools used in this course
Expected results / After the course
- Use in-house AI right away on tasks that security rules kept off AI
- Leave with an AI environment, on a personal PC or an in-house server, that you can use the next day
- Get clear criteria for sizing hardware, managing permissions and phasing adoption when you build an in-house AI server
About the instructor
Related courses
Start with an Online Course
Before you book on-site training, preview the essentials of this topic in an online course.
An introductory hands-on course for building work tools that run on plain conversational instructions.
Use AI in your daily work, from lesson prep to content creation.
We tailor this course to your company
From diagnosis to execution — Nanum Consulting
FAQ
Local LLM–Based AI Technical Training — Internal AI That Keeps Your Data Inside the Company
Work with materials you can’t upload to cloud AI, using AI on company PCs and servers
- Install and run open models on company PCs and servers, and understand an AI environment where data never leaves your organization
- Apply a Local LLM to report drafts, measurement result summaries, and technical document translation, and build the habit of verifying numerical and unit errors
- Practice connecting internal documents and software through RAG and API integration, and define your company’s adoption roadmap
- Use in-house AI right away on tasks that security rules kept off AI
- Leave with an AI environment, on a personal PC or an in-house server, that you can use the next day
- Get clear criteria for sizing hardware, managing permissions and phasing adoption when you build an in-house AI server
- In-house AI from a data security perspective
- Cloud AI vs. Local LLM
- Open model landscape (Gemma, Qwen, etc.)
- Internal AI Server Architecture
- Installing Ollama and LM Studio
- Choosing a small model and quantizing it
- (Server setup) Ollama server · Open WebUI · network access
- Drafting reports
- Summarizing measurement results
- Translating English technical documents
- Principles of prompt writing
- Verifying results
- Checking numbers and units for errors
- Comparing quality by model size
- RAG architecture
- Document chunking and embedding
- Connecting document folders and shared storage
- Q&A on sample documents
- Checking answer sources
- Ollama API
- Python Integration
- Automating report generation
- Integration with In-House Software
- Scope of personal PC use
- Server Sizing
- Access and permission management
- Phased adoption plan
- Q&A
