Current
Intermediate
Building AI Agents with Multimodal Models
NVIDIA Deep Learning Institute (DLI) · NVIDIA · Updated March 2026
Platform rating
4.6/5
AI Tutor Rating
8.6/10
Duration
8 hours instructor-led
Classes
24
Learn to build powerful AI agents using multimodal models that combine text, image, and video understanding for complex reasoning tasks.
What you'll get
Build AI agents using multimodal foundation models
Implement vision-language reasoning pipelines
Deploy multimodal agents for real-world tasks
Evaluate agent performance and reliability
Fit
Best for
Developers
AI Engineers
Data Scientists
Technical Builders
Not ideal for
Learners seeking only entry-level overviews
Prerequisites & pricing
Prerequisites
Python and deep learning experience
Pricing
Contact for pricing
Certification
Certificate
Growth Leverage: Completing this course positions you for roles such as AI Engineer, Machine Learning Scientist, or Data Scientist specializing in AI agents, opening doors to advanced certifications like NVIDIA's Jetson AI Specialist. It also prepares you for key positions in tech-driven industries requiring multimodal AI solutions.
Skills Value: Employers pay a premium for skills in multimodal AI development, with roles in this field offering salaries upwards of $120,000 due to high demand for AI agents in applications like autonomous systems and interactive AI, enabling companies to solve complex reasoning and automation problems effectively.
AI Agents
Multimodal AI
LLM
Computer Vision
NVIDIA