Designed and developed scalable AI-powered full-stack applications using Java, Spring Boot, React/Angular, REST APIs, and cloud-native technologies.
Integrated Generative AI and Large Language Models (LLMs) into enterprise applications to deliver intelligent search, content generation, recommendation, summarization, and conversational capabilities.
Built AI-enabled backend services using Java, Spring Boot, Spring AI, LangChain/LangGraph concepts, and RESTful APIs, ensuring secure and maintainable application architecture.
Developed Retrieval-Augmented Generation (RAG) solutions by integrating LLMs with enterprise documents, knowledge bases, vector databases, and semantic search.
Implemented prompt engineering, prompt templates, response validation, context management, and AI guardrails to improve accuracy, consistency, and reliability of AI-generated responses.
Developed responsive and reusable frontend components using React/Angular, TypeScript, JavaScript, HTML5, and CSS3, integrating them with AI-enabled backend services.
Designed microservices using Spring Boot, Spring Cloud, API Gateway, and service-to-service communication for highly scalable distributed applications.
Developed and consumed REST and event-driven APIs, integrating third-party AI platforms, enterprise systems, databases, and external services.
Worked with OpenAI/Azure OpenAI or equivalent LLM platforms, embedding models, vector search, and AI APIs into production applications.
Implemented vector-based knowledge retrieval using technologies such as Pinecone, Azure AI Search, Elasticsearch, or PostgreSQL with pgvector.
Designed data persistence solutions using PostgreSQL, MySQL, MongoDB, and Redis, selecting appropriate storage mechanisms based on application requirements.
Applied Spring Security, OAuth 2.0, JWT, RBAC, and API security practices to protect enterprise and AI-powered applications.
Implemented asynchronous and event-driven processing using Kafka, RabbitMQ, or cloud messaging services for high-volume workloads.
Containerized applications using Docker and deployed microservices to Kubernetes and cloud platforms such as AWS, Azure, or GCP.
Developed CI/CD pipelines using Jenkins, Maven, Git, GitHub/GitLab, and automated deployment workflows.
Implemented automated unit, integration, API, and end-to-end testing using JUnit, Mockito, REST Assured, Selenium, Playwright, or Cypress.
Added observability through logging, metrics, distributed tracing, health checks, and application monitoring, helping identify performance and AI-service issues.
Optimized application performance through caching, database tuning, API optimization, asynchronous processing, and efficient LLM/API utilization.
Collaborated with product managers, architects, data scientists, QA engineers, and DevOps teams to transform business requirements into production-ready AI solutions.
Requirements
5+ years of professional software development experience with strong expertise in Java and Spring Boot.
Strong hands-on experience building full-stack applications using Java, Spring Boot, REST APIs, React or Angular, JavaScript, and TypeScript.
Experience designing and developing microservices-based, scalable, and cloud-native applications.
Practical experience integrating Generative AI, Large Language Models (LLMs), and AI APIs into enterprise applications.
Strong understanding of RAG architecture, embeddings, vector databases, semantic search, prompt engineering, and LLM orchestration.
Experience working with OpenAI, Azure OpenAI, AWS Bedrock, Google Vertex AI, or similar AI platforms.
Knowledge of Spring AI, LangChain/LangGraph, or comparable AI application frameworks is highly desirable.
Experience developing and consuming RESTful APIs, JSON-based services, and third-party integrations.
Strong database experience with PostgreSQL, MySQL, MongoDB, Redis, or similar technologies.
Experience with Kafka, RabbitMQ, or other event-driven messaging platforms.
Hands-on experience with Docker, Kubernetes, CI/CD, Jenkins, Maven, Git, and cloud deployment.