Saoussen Chaabnia
AI/ML Solutions Engineer & Consultant
Tunis, Tunisia
Actions
I am an AI/ML Solutions Engineer and independent consultant with hands-on experience designing and deploying production-ready Data, ML and AI systems on Google Cloud. My expertise spans Generative AI, agentic and Multi-agent systems, MLOps, and Cloud-native ML architectures. I actively share real-world knowledge through technical articles, open-source projects, talks, and workshops, focusing on helping developers build scalable, practical AI solutions using Google technologies.
Badges
Area of Expertise
Topics
Building and Deploying Multi-Agent Systems with ADK and Vertex AI
This hands-on workshop teaches participants how to build, orchestrate, and deploy multi-agent AI systems using Google's Agent Development Kit (ADK) and Vertex AI Agent Engine. Attendees will learn how to create AI agents powered by Gemini models, build custom tools, and implement sequential, iterative, and parallel workflows. The workshop explores design pattern trade-offs, agent architecture decisions, callbacks and observability, memory management, and scalable deployment. It is structured around 10 progressive Jupyter notebooks and concludes with a full-stack capstone project deployed to Google Cloud using Agent Engine for agents and Cloud Run with a React and FastAPI stack for the frontend and backend.
Key takeaways
• Build and orchestrate multi-agent AI systems with Google ADK
• Create custom tools and coordinate agent teams powered by Gemini models
• Choose between LLM-driven and workflow-driven design patterns (Sequential, Parallel, Iterative)
• Navigate agent architecture trade-offs: Sub-agents vs. Agent as a Tool
• Implement callbacks, observability, and guardrails for production readiness
• Master session management, state, artifacts, and short-term vs. long-term memory
• Deploy production-ready full-stack AI systems on Google Cloud (Agent Engine + Cloud Run)
DevFest Ahlen 2025
A technical talk and live demonstration on designing and deploying distributed multi-agent systems using Google’s AI stack.
The session covered :
- Practical introduction to Google ADK for agent development with Gemini 2.5 Flash
- Agent-to-Agent (A2A) Protocol for distributed agent communication
- Model Context Protocol (MCP) for integrating external tools like Notion
- Deployment strategies for Vertex AI Agent Engine and Cloud Run
Demonstrated a live system where one orchestrator on Vertex AI Agent Engine coordinates 5 specialist agents on Cloud Run to generate complete and complex social media campaigns from a single prompt and showed how agents collaborate, delegate tasks, and scale beyond monolithic LLM applications.
Attendees learned how to build scalable, distributed AI systems using Google's AI stack with working code examples. They gained understanding of emerging technologies like A2A Protocol and Model Context Protocol (MCP), how they work together to build sophisticated agentic systems. They also had practical guidance on architecture patterns, tooling, and production considerations for agentic systems on Google Cloud.
DevFest Fusion 4.0 2025
A hands-on workshop teaching attendees how to build production-ready multi-agent AI systems using Google's Agent Development Kit (ADK) and Vertex AI Agent Engine.
Participants learned to create and orchestrate AI agents powered by Gemini models, build custom tools, and implement sequential, iterative, and parallel workflows.
The workshop included 8 progressive Jupyter notebooks culminating in a capstone project: a full-stack Content Creation Studio that automates blog posts, social media content, email newsletters, and SEO metadata generation. Attendees deployed their systems to Google Cloud using Agent Engine and Cloud Run with React/FastAPI stack.
Participants left with practical skills to design, build, and deploy multi-agent systems for real-world automation use cases.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top