Akshay Darla

Bridging Data Science and Software Engineering: LLM-Powered Java Applications in Production.

Abstract: 

As Large Language Models reshape the landscape of modern software development, the divide between Data Science and Software Engineering is rapidly narrowing. This presentation explores how Java developers can bridge that gap by integrating LLMs directly into production-grade microservices using frameworks including Spring AI and LangChain4j. Drawing on real-world implementations, we examine Retrieval-Augmented Generation pipelines, vector database integration, and intelligent API design patterns. We also address practical challenges including latency management, hallucination mitigation, data privacy, and observability. Attendees will leave with a concrete architecture blueprint and actionable strategies for deploying LLM-powered Java applications that are scalable, reliable, and enterprise-ready.

Profile: 

I am a Sr. Software Engineer at Tata Consultancy Services, holding a Master's degree in Computer Science from Western Illinois University. I support and modernize enterprise insurance platforms for Pacific Life, handling production incident resolution and development of scalable application components. I work extensively with Java/J2EE, Spring Boot microservices, IBM WebSphere, REST/SOAP APIs, and Agile methodologies. My experience includes data engineering with Kafka Streams and Kafka Connect, Cassandra and relational databases, and system integration using JSON and XML. I also support AWS-based deployments, monitoring, and automation, and leverage AI-assisted testing, CI/CD tools, and intelligent monitoring to improve performance, reliability, and operational efficiency of enterprise systems.