Agentic AI on the NVIDIA Stack
Build and profile AI agents using NVIDIA NIM models and the open-source NeMo Agent toolkit alongside frameworks such as LangGraph.
- ✓ 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: Mon, 04 Jan 2027 · 32 hours · 4 days
Agentic AI on the NVIDIA Stack
Duration: 32 hours · 4 days
Next batch: Mon, 04 Jan 2027
Format: Online live · Bengaluru classroom
Modules: 8 · Topics: 38
Level: Advanced
Fee: ₹14,999
Trusted by leading experts
Upcoming batches
Open batches for individuals; corporate batches on your dates.
| Programme | Starts | Mode | Schedule | Duration | |
|---|---|---|---|---|---|
| Agentic AI on the NVIDIA Stack | Mon, 04 Jan 2027 | Bengaluru classroom | Weekday | 4 days | Enquire |
| Agentic AI on the NVIDIA Stack | Sat, 06 Feb 2027 | Online live | Weekend (Sat) | 5 Saturdays | Enquire |
| Agentic AI on the NVIDIA Stack | Wed, 24 Mar 2027 | Online live | Weekday | 4 days | Enquire |
Soaring demand, and where it takes you
Agentic AI is a priority for many enterprises, and engineers who can build agents that are observable and efficient on GPU infrastructure are in demand.
Become an expert
Roles this programme prepares you for:
Become a Agentic AI Engineer
Builds and optimises agent workflows.
- Explain agent architectures and where NVIDIA tools fit
- Use NIM models for reasoning and tool calling
- Compose agents and tools with the NeMo Agent toolkit
About the course
Build AI agents on the NVIDIA stack: use NIM-hosted models for reasoning and tool calling, compose agents with the open-source NeMo Agent toolkit alongside frameworks such as LangGraph, and profile, evaluate and guard agent workflows.
Build and profile AI agents using NVIDIA NIM models and the open-source NeMo Agent toolkit alongside frameworks such as LangGraph.
Why should I attend?
AI and ML engineers
Python developers building agents
Platform engineers
Solution architects
Prerequisites
Python; experience building an LLM or agent app; Docker
Level
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 agent architectures and where NVIDIA tools fit
- Use NIM models for reasoning and tool calling
- Compose agents and tools with the NeMo Agent toolkit
- Integrate with frameworks such as LangGraph
- Profile and evaluate agent workflows
- Apply guardrails to agent behaviour
Skills you will gain
Agents
NVIDIA tooling
Operations
Tools and platforms covered
LangGraph
Python
DockerCourse curriculum
M01 Agent architectures
- Agent loops
- Single and multi-agent
- The NVIDIA agent stack
- Planning patterns
- Reference blueprints
🧪 Hands-on: Map an agent design
M02 Models for agents
- Reasoning and tool calling with NIM
- Model choice
- Latency
- Structured output reliability
- Small vs large models for agents
🧪 Hands-on: Call tools via a NIM model
M03 NeMo Agent toolkit
- Workflows and functions
- Framework integration
- Configuration
- YAML workflow configuration
- Custom functions
🧪 Hands-on: Compose an agent workflow
M04 Profiling and evaluation
- Profiling agent runs
- Evaluation datasets
- Optimisation
- Token and latency profiling
- Regression suites
🧪 Hands-on: Profile and optimise a workflow
M05 Guardrails
- Safety and topic rails for agents
- Tool permissions
- Testing
- Prompt-injection defences
- Approval steps
🧪 Hands-on: Add guardrails
M06 Deployment
- Serving agents
- Scaling
- Monitoring
- Containerising agents
- Cost monitoring
🧪 Hands-on: Deploy and monitor
M07 Agentic RAG and tools
- Retrieval tools
- Calling enterprise APIs
- MCP integration
- Error handling
🧪 Hands-on: Build an agent that combines retrieval and an internal API
M08 Capstone: NVIDIA-stack agent
- Design
- Build
- Profile and optimise
- Present
🧪 Hands-on: Deliver a profiled, guarded agent on NIM endpoints
Certification preparation
This course covers topics that can help participants prepare for the NVIDIA-Certified Professional: Agentic AI (NCP-AAI) 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
Profiled multi-step agent
An agent with tool use, guardrails and a profiling 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 Agentic AI on the NVIDIA Stack. [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
Is this an NVIDIA course?
No. It is an independent Learning Dots course that teaches NVIDIA technologies.
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 AI agents on the NVIDIA stack: use NIM-hosted models for reasoning and tool calling, compose agents with the open-source NeMo Agent toolkit alongside frameworks such as LangGraph, and profile, evaluate and guard agent workflows.
What is Agentic AI on the NVIDIA Stack?
Build and profile AI agents using NVIDIA NIM models and the open-source NeMo Agent toolkit alongside frameworks such as LangGraph.
Who this course is for
AI and ML engineers, Python developers building agents, Platform engineers, Solution architects.
What you will be able to do
Explain agent architectures and where NVIDIA tools fit. Use NIM models for reasoning and tool calling. Compose agents and tools with the NeMo Agent toolkit. Integrate with frameworks such as LangGraph. Profile and evaluate agent workflows. Apply guardrails to agent behaviour.
Career paths
Roles this course supports include Agentic AI Engineer, AI Platform Engineer, AI Solutions Architect. Agentic AI is a priority for many enterprises, and engineers who can build agents that are observable and efficient on GPU infrastructure are in demand.
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.