Building and Serving LLM Apps with NVIDIA NIM & NeMo
Deploy models as NVIDIA NIM inference microservices and customise, evaluate and guard them with NeMo tools.
- ✓ Instructor-led live sessions, online or in Bengaluru
- ✓ Hands-on labs in every module
- ✓ Capstone project with trainer review
- ✓ Curriculum customisable for corporate teams
- ✓ Certificate of completion
Next batch: Sat, 12 Dec 2026 · 32 hours · 4 days
Building and Serving LLM Apps with NVIDIA NIM & NeMo
Duration: 32 hours · 4 days
Next batch: Sat, 12 Dec 2026
Format: Online live · Bengaluru classroom
Modules: 8 · Topics: 38
Level: Intermediate to Advanced
Fee: ₹14,999
Trusted by leading experts
Upcoming batches
Open batches for individuals; corporate batches on your dates.
| Programme | Starts | Mode | Schedule | Duration | |
|---|---|---|---|---|---|
| Building and Serving LLM Apps with NVIDIA NIM & NeMo | Sat, 12 Dec 2026 | Online live | Weekend (Sat) | 5 Saturdays | Enquire |
| Building and Serving LLM Apps with NVIDIA NIM & NeMo | Mon, 25 Jan 2027 | Bengaluru classroom | Weekday | 4 days | Enquire |
| Building and Serving LLM Apps with NVIDIA NIM & NeMo | Sat, 06 Mar 2027 | Online live | Weekend (Sat) | 5 Saturdays | Enquire |
Soaring demand, and where it takes you
Enterprises standardising on GPU infrastructure need engineers who can deploy and customise models efficiently on that stack.
Become an expert
Roles this programme prepares you for:
Become a GenAI Platform Engineer
Deploys and manages model microservices for applications.
- Explain the roles of NIM, NeMo and the NVIDIA API catalog
- Deploy NIM microservices and call their APIs
- Build RAG with NIM embedding, re-ranking and LLM endpoints
About the course
Build and serve generative AI applications on NVIDIA's stack: deploy NVIDIA NIM inference microservices with OpenAI-compatible APIs, build RAG with NIM embedding and re-ranking endpoints, customise models with NeMo tools and add safety controls with NeMo Guardrails.
Deploy models as NVIDIA NIM inference microservices and customise, evaluate and guard them with NeMo tools.
Why should I attend?
ML and MLOps engineers
AI application developers
Platform engineers
Architects designing on NVIDIA infrastructure
Prerequisites
Python; Docker; basic LLM and RAG concepts; Kubernetes helpful
Level
Intermediate to Advanced
Delivery modes, duration and fee
Online live
Instructor-led virtual classroom; weekday (full-day) or weekend (Saturday) batches
Bengaluru classroom
In-person batches at our Bengaluru training venue
On-site at your office
Private corporate batch anywhere in India, scheduled around your teams
Blended
Live sessions plus guided self-paced labs and mentor check-ins
Duration: 32 hours · 4 days
Course fee (open batch): ₹14,999
Corporate / team batches: per-participant or flat batch pricing on request, based on group size, format and customisation.
What will you learn
- Explain the roles of NIM, NeMo and the NVIDIA API catalog
- Deploy NIM microservices and call their APIs
- Build RAG with NIM embedding, re-ranking and LLM endpoints
- Customise models with NeMo (for example LoRA)
- Evaluate customised models
- Add NeMo Guardrails for safety and topic control
Skills you will gain
Serving
Customisation
Safety
Tools and platforms covered
Docker
Kubernetes
Python
LangChainCourse curriculum
M01 The NVIDIA GenAI stack
- NIM, NeMo and API catalog
- Licensing overview
- Reference architectures
- Choosing models from the catalog
- Hardware sizing
🧪 Hands-on: Explore hosted endpoints
M02 Running NIM
- Pulling and running containers
- OpenAI-compatible APIs
- Scaling on Kubernetes
- Model profiles and optimisation
- Helm-based deployment
🧪 Hands-on: Deploy an LLM NIM
M03 RAG with NIM
- Embedding and re-ranking NIMs
- Vector store integration
- Prompt assembly
- Hybrid search
- Evaluation of retrieval
🧪 Hands-on: Build a RAG pipeline
M04 Customising with NeMo
- Data preparation
- LoRA customisation
- Evaluation
- Dataset curation
- Comparing adapters
🧪 Hands-on: Customise and evaluate a model
M05 Guardrails
- NeMo Guardrails concepts
- Topic and safety rails
- Testing rails
- Jailbreak rails
- Fact-checking rails
🧪 Hands-on: Add guardrails to the app
M06 Production considerations
- Monitoring
- Cost and capacity
- Security
- Observability
- Upgrades and versioning
🧪 Hands-on: Production readiness review
M07 Multimodal and speech
- Vision-language NIMs
- Speech AI overview
- Document parsing pipelines
- Use cases
🧪 Hands-on: Add document-image parsing to a RAG pipeline
M08 Capstone: enterprise LLM app on NIM
- Architecture
- Build
- Guardrails and evaluation
- Deployment demo
🧪 Hands-on: Deliver a guarded RAG app served on NIM
Certification preparation
This course covers topics that can help participants prepare for the NVIDIA-Certified Associate: Generative AI LLM (NCA-GENL) exam, which is run by NVIDIA. Check the current exam guide on nvidia.com. Passing is not guaranteed and the exam fee is not included unless stated. [confirm]
Hands-on projects
Guarded RAG assistant
A RAG assistant served on NIM endpoints with guardrails and an evaluation report.
Why train with us
Built around your stack
Labs and examples adapted to the tools, cloud and data your team actually uses.
Practice-first
Every module ends in a lab, and the course ends with a reviewed capstone.
Practitioner-led
Delivered by Karthick Selvam and vetted specialist trainers from our network.
Visible progress
Attendance, lab completion and assessment results shared with your L&D team.
Certificate of completion
Participants who complete the labs and capstone receive a Learning Dots certificate of completion for Building and Serving LLM Apps with NVIDIA NIM & NeMo. [confirm certificate wording / sample image]
Learner reviews
“[Verified learner review for this course]”
“[Verified learner review for this course]”
Meet your trainer
Karthick Selvam
Founder · Data Engineering Corporate Trainer, Bengaluru
[Trainer bio, experience and areas of expertise]
Frequently asked questions
Do we need on-premise GPUs?
No. Hosted endpoints can be used for learning; self-hosted NIM requires NVIDIA GPUs and appropriate licensing.
Can the curriculum be customised for our team?
Yes. Modules, depth, duration and labs can be tailored to your stack and goals.
What delivery formats are available?
Online live instructor-led sessions, Bengaluru classroom, or on-site at your office.
How do we enquire or book?
Use the enquiry form on this page or the Enquire button next to any batch.
What does it cost?
The open-batch fee is ₹14,999 per participant plus GST. Corporate batches are priced on group size, format and customisation.
How long is the course?
32 hours · 4 days. Corporate batches can be split into half-day sessions.
A closer look
About this course
Build and serve generative AI applications on NVIDIA's stack: deploy NVIDIA NIM inference microservices with OpenAI-compatible APIs, build RAG with NIM embedding and re-ranking endpoints, customise models with NeMo tools and add safety controls with NeMo Guardrails.
What is Building and Serving LLM Apps with NVIDIA NIM & NeMo?
Deploy models as NVIDIA NIM inference microservices and customise, evaluate and guard them with NeMo tools.
Who this course is for
ML and MLOps engineers, AI application developers, Platform engineers, Architects designing on NVIDIA infrastructure.
What you will be able to do
Explain the roles of NIM, NeMo and the NVIDIA API catalog. Deploy NIM microservices and call their APIs. Build RAG with NIM embedding, re-ranking and LLM endpoints. Customise models with NeMo (for example LoRA). Evaluate customised models. Add NeMo Guardrails for safety and topic control.
Career paths
Roles this course supports include GenAI Platform Engineer, LLM Application Developer, AI Safety Engineer. Enterprises standardising on GPU infrastructure need engineers who can deploy and customise models efficiently on that stack.
NVIDIA & GPU Computing guides
What Is CUDA?
CUDA is NVIDIA's parallel computing platform and programming model for running general-purpose code on NVIDIA GPUs.
What Is NVIDIA RAPIDS?
RAPIDS is a suite of open-source libraries from NVIDIA for GPU-accelerated data science and analytics.
What Are NVIDIA NIM and NeMo?
NIM and NeMo are parts of NVIDIA's software stack for generative AI: NIM for serving models, NeMo for building and customising them.
TensorRT, TensorRT-LLM and Triton Explained
Three NVIDIA technologies for fast, scalable AI inference.