[In-Person - March] Java Meet-up at Devon Softwares
Details
## Join us for an exciting sessions on AI Native JAVA meet-up, in collaboration with Devon Software Service
## Details
Location:
DevOn Software Services Pvt. Ltd.
Lower Ground Floor,
Building 2A - West Tower,
Embassy Tech Village,
Deverabeesanahalli, Bellandur,
Bengaluru - 560087
Note: *** Event from 9.30am to 3.30pm, Lunch Provided ***
-- RSVP ONLY IF HAVE YOU DECIDED TO JOIN --
-- ITS A FREE EVENT, RSVP before 13th MARCH 2026 --
-- GOV ID CARD IS MANDATORY TO ENTER --
--ATTENDEES CAN BRING LAPTOPS(FULLY CHARGED) ONLY IF THEY WISH TO CODE IN PARALLEL, BUT IT'S NOT MANDATORY--
Agenda:
➡️ Registration Opens @ 9.30 am
Talk #1: From REST APIs to AI Agents: Building Intelligent Java Applications with LangChain4j
AI is no longer limited to chatbots - it is becoming a core part of application architecture. But how can Java developers move beyond simple API calls and build intelligent, context-aware systems?
In this session, we explore how LangChain4j helps transform traditional Java applications into AI-powered systems with memory, document retrieval (RAG), and tool integration. Through real-world examples and architecture discussions, we will see how to design scalable AI workflows inside Spring Boot applications.
Whether you’re building internal copilots, AI-driven automation, or knowledge assistants, this talk will show you how to bring modern AI capabilities into the Java ecosystem.
Time: 10.00 am to 11.00 am
Speaker(s) :
Sumanth K S and Giridhar Gopal
Talk #2: Inside Tomorrow’s AI Systems: Tools, MCP & Skills (Spring)
Tomorrow’s AI systems rely on structured tools, protocol-driven orchestration, and reusable skills. This session explores these concepts using Spring AI with Java, showing how to design production-ready, scalable AI applications within the Spring ecosystem. Includes a focused demo and architectural walkthrough.
Time: 11.00 pm to 12.00 pm
Speaker(s) :
Muthukumaran Navaneethakrishnan and Shaama M
Talk #3: LLM serving using DJL
Integrating machine learning into Java environments often feels like a mismatch of tools. This talk explores the Deep Java Library (DJL), an open-source framework that enables high-performance model serving natively on the JVM and build inference pipelines. We will dive into DJL Serving, a standalone solution designed to handle dynamic batching and auto-scaling without the latency of Python-to-Java bridges. Learn how to deploy models from PyTorch, TensorFlow, and ONNX using a unified, engine-agnostic API.
Time: 12.00 pm to 1.00 pm
Speaker(s) :
Jayakrishnan Ramakumar
Break: Lunch
Time: 1:00pm - 2:00pm
Networking
Time: 2:00pm to 3:30pm
