Svethalina Gurram

Engineered Java and Spring Boot microservices integrating Generative AI capabilities through OpenAI, Azure OpenAI, and Anthropic APIs, enabling LLM-powered enterprise workflows. Architected RESTful services using Spring Boot, Spring MVC, Spring Data JPA, PostgreSQL, and Redis to support scalable AI-enabled applications and workflow orchestration. Enhanced services with RAG and GraphRAG using embeddings, vector databases, semantic search, hybrid retrieval, BM25, and reranking to improve contextual relevance. Orchestrated agentic AI workflows using LangChain, LangGraph, LlamaIndex, and CrewAI with tool/function calling, ReAct patterns, and agent memory to automate multi-step processes. Implemented security and governance with Spring Security, OAuth 2.0, JWT, RBAC, PII protection, and prompt-injection mitigation, and operationalized services with Docker, Kubernetes, Terraform, GitHub Actions, OpenTelemetry, Grafana, LangSmith, and MLflow for monitoring and LLM evaluation.

Spearheaded Java and Spring Boot services integrating Azure OpenAI, OpenAI, and Anthropic APIs for LLM-powered enterprise applications. Designed AI-powered REST APIs and microservices using Java, Spring Boot, Spring MVC, Spring Data JPA, PostgreSQL, and Redis, incorporating LLM inference, prompt orchestration, structured outputs, and asynchronous processing. Established RAG pipelines with embeddings, vector databases, semantic search, hybrid retrieval, BM25, and reranking to improve retrieval precision. Orchestrated agentic AI workflows using LangChain, LangGraph, LlamaIndex, function/tool calling with ReAct patterns, and agent memory to automate multi-step business processes. Hardened applications with Spring Security, OAuth 2.0, JWT, RBAC, prompt validation, PII protection, guardrails, and prompt-injection mitigation. Streamlined deployment using Docker, Kubernetes, Terraform, GitHub Actions, AWS, and added observability and evaluation with OpenTelemetry, Grafana, LangSmith, and MLfl

Programmed Java and Spring Boot backend services using Spring MVC, Spring Data JPA, Hibernate, and SQL, improving application processing efficiency. Built REST APIs and microservices using Java, Spring Boot, JSON, HTTP, and enterprise integration patterns to create reusable, scalable components across AWS environments. Automated backend data-processing workflows using Java, SQL/PostgreSQL, asynchronous processing, and AWS services, reducing recurring manual processing time. Tuned SQL queries, Hibernate/JPA data-access logic, API processing, and backend components to improve response performance, database efficiency, and reliability. Improved code quality and delivery using JUnit, Mockito, Git, code reviews, CI/CD pipelines, AWS deployment practices, and Agile/Scrum.