Overview

Multimodal AI Engineering: Practical Systems and Tools for Developers and AI Engineers is a technical guide for building production-ready multimodal systems that go beyond research prototypes. This book is written for engineers and practitioners who want to understand not just the models, but the infrastructure and workflows that make multimodal AI reliable at scale. Inside, you will learn how to: Combine Large Language Models (LLMs) with Small Language Models (SLMs) to balance reasoning depth, cost, and latency. Build multi-agent workflows that coordinate specialized models for planning, reasoning, and execution. Integrate vector databases (FAISS, Weaviate, Pinecone, Qdrant, Milvus) as scalable memory and retrieval systems. Orchestrate agents and tools using LangGraph, AutoGen, Semantic Kernel, and MCP. Optimize serving pipelines with vLLM, TGI, OpenVINO, and MediaPipe for both cloud and edge deployments. Apply MLOps frameworks such as MLflow, BentoML, and Seldon Core to ensure reproducibility, observability, and governance. Establish guardrails and safety practices to mitigate hallucinations, enforce compliance, and manage risks. The book emphasizes system design trade-offs, performance optimization, and deployment strategies, making it especially valuable for: AI Engineers who need to move beyond single-model prototypes. Software Developers integrating multimodal capabilities into existing applications. Technical Managers evaluating infrastructure choices for AI adoption. Researchers interested in bridging cutting-edge models with applied systems. Multimodal AI is not optional, it is rapidly becoming the default architecture for real-world AI. This book provides the tools, design principles, and engineering practices you need to build smarter, faster, and more efficient AI systems.

Full Product Details

9798262122585

Table of Contents

Reviews

Author Information

Tab Content 6

Countries Available