Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

For organisations on Google Cloud or storing data in BigQuery and Cloud Storage, Vertex AI delivers the long-context and multimodal capabilities of Gemini models alongside enterprise IAM, VPC Service Controls and data residency guarantees. This course covers the unified Google Gen AI SDK, response schemas and function calling, Context Caching, enterprise grounding with Vertex AI Search and RAG Engine, and open models in Model Garden.

Participants build an end-to-end application on Google Cloud connected securely to enterprise data and evaluated with the Vertex AI Gen AI Evaluation Service.

Who Should Attend?

  • Software, data and AI engineers building services on Google Cloud (GCP)
  • Cloud architects designing solutions across BigQuery, Cloud Storage and Vertex AI
  • Teams leveraging multimodal (document, image, video, audio) and long-context capabilities at scale
  • Prerequisite: familiarity with core Google Cloud concepts and Python or TypeScript

Key Takeaways

  • Use the Google Gen AI SDK for structured outputs, thinking budget control and tool calling on Gemini
  • Reduce cost on large document and media workloads using Vertex AI Context Caching and Batch Prediction
  • Produce grounded answers with citations via Vertex AI Search, RAG Engine or BigQuery vector search
  • Configure enterprise security boundaries with IAM, Service Accounts, CMEK and VPC Service Controls
  • Evaluate model and prompt changes quantitatively with the Vertex AI Gen AI Evaluation Service

Curriculum

The Vertex AI Ecosystem and Google Gen AI SDK
  • The Gemini model family (Flash, Pro, thinking modes) and Vertex AI Model Garden (Claude, Llama, Gemma)
  • Text, multimodal inputs and streaming calls with the unified `google-genai` SDK
Controlled Generation, Function Calling and Context Caching
  • Strict JSON generation via `response_schema` and parallel/automatic function calling
  • Implicit and explicit Context Caching to cut cost and latency on large inputs
Grounding, Vertex AI Search and BigQuery Integration
  • Enterprise grounding with Vertex AI Search and Vertex AI RAG Engine
  • In-warehouse LLM processing using BigQuery Vector Search and `ML.GENERATE_TEXT`
Vertex AI Agent Engine and Evaluation
  • Deploying tool-using agents with the Agent Development Kit (ADK) and Agent Engine
  • Rule-based and judge-based quality measurement with the Gen AI Evaluation Service
GCP Enterprise Security, Quotas and Cost Control
  • IAM, Workload Identity, CMEK, VPC Service Controls and zero data retention settings
  • Dynamic Shared Quota (DSQ), Provisioned Throughput and Cloud Monitoring/Logging
Hands-On: Enterprise Knowledge and Analytics Service on Vertex AI
  • Building a Gemini + Grounding + Evaluation pipeline for an internal scenario
  • Production architecture and cost profile review

Other Courses in This Category

  • Production Architecture Patterns for Enterprise LLM Systems

    Architectural patterns for turning LLM prototypes into resilient enterprise systems: AI gateways, async queues, circuit breakers, fallback chains, idempotency, guardrails and OpenTelemetry tracing.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Large Language Model (LLM) Fundamentals

    How foundation models and LLMs work: tokens, context windows, sampling, hallucination, model families and when to choose prompting, RAG or fine-tuning — a hands-on starting point for technical teams.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Large Language Models and the Transformer Architecture

    A technical deep dive into the transformer: tokenization, self-attention, RoPE, KV cache, scaling laws, SFT, RLHF/DPO and reasoning models, explored hands-on with PyTorch and Hugging Face Transformers.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Building Applications with LLM APIs

    Hands-on programme for building a near-production LLM application with the OpenAI, Anthropic Claude and Google Gemini APIs, covering streaming, conversation state, retries, rate limits, fallbacks and basic evals.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Structured Outputs with LLMs: JSON Schema, Pydantic and Constrained Decoding

    Getting reliable JSON from LLMs with JSON Schema, OpenAI Structured Outputs, Gemini response schemas, Pydantic/Zod, Instructor and constrained decoding, plus validation, repair loops and document data extraction.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • LLM Tool Use and Function Calling

    How to let LLMs safely call APIs, databases and internal systems via tool/function calling: tool schema design, parallel calls, MCP servers, error handling and permission boundaries.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View

Get in touch