Sijohn Mathew
Public Speaker, Co-Founder & Head of Product Innovation @ AclarityTech, Cloud Architect specialized in App Development and Modernisation with a touch of AI
Stockholm, Sweden
Actions
I am a Cloud Architect who has navigated the major paradigm shifts in software engineering—from the early days of monolithic development through the rise of microservices, and now into the current frontier of Agentic AI. Based in Stockholm, I currently design retail technology solutions at Aclarity, where I focus on leveraging the full potential of the Google Cloud ecosystem.
As an 8x Google Cloud Certified Architect, I’m driven by practical experimentation. My recent work centers on implementing Agentic AI and serverless architectures to solve complex, high-scale data challenges. I enjoy breaking down these advanced cloud concepts into actionable insights and sharing what I learn with the developer community.
Area of Expertise
Topics
Accelerate AI with Serverless: Deploying Scalable AI Applications on Google Cloud Run
This talk dives into the power of serverless technologies on Google Cloud, with a focus on using Cloud Run to efficiently build and deploy AI applications. As a fully managed, auto-scaling container service, Cloud Run eliminates the need for infrastructure management and adapts to the dynamic, often unpredictable demands of AI workloads. Attendees will learn how Cloud Run’s serverless architecture is particularly suited to AI, offering a cost-effective, pay-per-use model that scales based on demand.
Through engaging demos, this session showcases the versatility and ease of using Cloud Run for AI:
Gemini-powered Chat Application
Asynchronous AI with Cloud Run Jobs for batch processing
Function Calling with LLMs
Attendees will leave with insights into the benefits of Cloud Run for scalable AI deployment, tips for leveraging Google Cloud’s client libraries and buildpacks, and practical steps for integrating Cloud Run into their AI projects.
Agentic AI: Build an AI-Powered Receipt Processing Agent with ADK on Cloud Run & Gemini in Vertex AI
This session guides you through building a sophisticated, multi-agent system to automate receipt processing using the Google Agent Development Kit (ADK). You will learn to orchestrate specialized AI agents powered by Gemini to perform multimodal data extraction from receipt images, classify expenses, and log the structured data into BigQuery. This hands-on experience will teach you the fundamentals of creating modular, tool-augmented AI workflows for real-world automation
In-person, Virtual
Accelerate AI with Cloud Run: Deploying MCP-Enabled ADK Agents
Discover how to combine the power of the Agent Development Kit (ADK) and Cloud Run to build scalable, production-ready AI agents. In this session, we’ll explore a hands-on example where an AI “tour guide” agent interacts with a Model Context Protocol (MCP) server that delivers zoo animal data. You’ll learn how to separate reasoning from tooling by hosting the MCP server on Cloud Run and integrating it with an ADK-powered agent for secure, efficient communication.
By the end of this session, you’ll understand:
• How to design and deploy an MCP server on Cloud Run.
• How to connect ADK agents with remote tools for dynamic data retrieval.
• Best practices for building scalable, cost-efficient AI agents ready for production environments.
Whether you’re an AI developer or a cloud architect, this session will help you accelerate your journey to building real-world, agentic AI solutions with Google Cloud.
• First Delivery: Part of Google’s Accelerate AI with Cloud Run program.
• Technical Level: Intermediate – familiarity with Python/Node.js
• Target Audience: AI developers, cloud architects, and solution engineers exploring agentic AI solutions.
• Duration: 45–60 minutes (including demo and Q&A).
From Chatbots to Teams of AI: Building Self-Correcting Multi-Agent Systems with ADK & A2A
Most AI demos today focus on a single chatbot answering questions. But real-world problems are rarely solved by one “smart” assistant.
In this session, we’ll explore how multiple AI agents can work together like a real team — each with a clear role — to solve complex tasks more reliably. Just like humans, some agents research, some review, some create content, and one coordinates the entire process.
Using a practical example of an AI-powered course creation system, you’ll see how agents can collaborate, review each other’s work, fix mistakes, and produce better results than a single AI model acting alone.
We’ll walk through building a distributed multi-agent system using Google’s Agent Development Kit (ADK) and the Agent-to-Agent (A2A) protocol.
The system is composed of specialized agents:
A Researcher Agent that uses web search tools to gather up-to-date information
A Judge Agent that evaluates research quality using structured outputs (Pydantic)
A Content Builder Agent that turns validated research into structured content
An Orchestrator Agent that manages control flow and agent collaboration
You’ll see how LoopAgent enables self-correction through feedback loops, how SequentialAgent orchestrates higher-level workflows, and how agents communicate over A2A instead of relying on a single monolithic prompt.
We’ll also cover how to run the system locally and deploy it to Google Cloud Run, making the architecture production-ready and scalable.
This session is targeted at developers and architects with basic familiarity with large language models and cloud-native applications. No prior experience with multi-agent frameworks is required. The session is designed as a 30–45 minute talk with optional demo segments. Code examples are simplified for clarity and focus on architecture and orchestration patterns. This session has not been previously delivered publicly.
From Data to Decisions: Launching a Bakery with AI Agents, BigQuery & Google Maps
What if you could ask an AI for real business advice — not just opinions, but decisions grounded in data and real-world context?
In this session, we’ll explore how an AI agent can help answer a practical question many entrepreneurs face: Where should I open my business, and will it actually work?
We will see how AI can analyze market trends, customer demographics, pricing strategies, and even neighborhood-level location details to make informed recommendations.
Behind the scenes, the solution is built using the Agent Development Kit (ADK) with remote MCP servers that connect the agent to enterprise data in BigQuery and real-world geospatial context via Google Maps APIs, all orchestrated by Gemini on Vertex AI.
The agent autonomously:
Queries BigQuery datasets to discover macro trends like demographics, competitor pricing, and historical sales patterns
Uses Google Maps to validate micro-level location details such as nearby competitors and neighborhood activity
Synthesizes insights into a single, grounded business recommendation
We’ll walk through the architecture, orchestration flow, and deployment model, showing how this approach enables trustworthy, explainable AI decisions that go far beyond traditional RAG or single-model chat applications.
This session is intended for developers, data engineers, architects, and technical decision-makers interested in agentic AI and data-driven systems. Basic understanding of cloud analytics and APIs is helpful but not mandatory. The session works best as a 30–45 minute talk with a live demo. The business scenario and datasets are illustrative and used for demonstration purposes. This session may be delivered as a live or recorded demo depending on event setup.
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