Gen AI Java Developer

Capgemini•Atlanta, GA

8d•Onsite

About The Position

GenAI Backend & Platform Development: Design, build, and maintain enterprise-grade GenAI-powered backend services using Java (Spring Boot) and cloud-native architectures. Develop RESTful and event-driven APIs using Spring Boot, Spring WebFlux, and Kafka/streaming platforms. Implement GenAI use cases such as conversational assistants and copilots integrated into enterprise systems, Retrieval-Augmented Generation (RAG) pipelines for knowledge-driven applications, and agent-based automation for workflow execution and decision support. Integrate LLM services (Azure OpenAI, OpenAI, Anthropic, etc.) into Java-based microservices using secure, scalable patterns. LLM Orchestration & Workflow Engineering: Build and orchestrate multi-step GenAI workflows using LangChain (via Java/Python interoperability or service-based architecture) or custom Java-based orchestration layers and state machines. Design and manage tool calling and agent execution frameworks, context, memory, and prompt lifecycle management, and conditional routing, fallback logic, retries, and resilience mechanisms. Ensure workflows are robust, observable, and production-ready at scale. Cloud-Native & DevOps Engineering: Develop and deploy services on cloud platforms (Azure preferred) using containers (Docker) and orchestration (Kubernetes / AKS), and managed cloud services for AI, messaging, storage, and security. Build and maintain CI/CD pipelines using tools such as GitHub Actions / Azure DevOps / Jenkins, including automated build, test, security scan, and deployment stages. Apply Infrastructure as Code principles using Terraform, Bicep, or ARM templates. Ensure high availability, scalability, and cost efficiency of GenAI services. Engineering Excellence & Governance: Write clean, maintainable, and testable Java code adhering to SOLID and clean architecture principles. Implement unit, integration, and contract tests, as well as API and workflow-level automated testing. Monitor and enforce code quality, security, and compliance standards, as well as logging, metrics, and distributed tracing for GenAI services. Participate in code reviews, design discussions, and architecture governance.

Requirements

5 to 8 years of professional software engineering experience
Strong expertise in Java, with hands-on experience in Spring Boot / Spring Cloud
Experience building and operating cloud-native microservices
Solid understanding of API design, asynchronous processing, and distributed systems

Nice To Haves

Azure preferred cloud platform
Experience with LangChain (via Java/Python interoperability or service-based architecture)
Experience with custom Java-based orchestration layers and state machines
Experience with Terraform, Bicep, or ARM templates
Experience with GitHub Actions / Azure DevOps / Jenkins
Experience with Docker and Kubernetes / AKS
Experience integrating LLM services (Azure OpenAI, OpenAI, Anthropic, etc.)
Experience with Kafka/streaming platforms
Experience with SOLID and clean architecture principles

Responsibilities

Design, build, and maintain enterprise-grade GenAI-powered backend services using Java (Spring Boot) and cloud-native architectures
Develop RESTful and event-driven APIs using Spring Boot, Spring WebFlux, and Kafka/streaming platforms
Implement GenAI use cases such as conversational assistants and copilots integrated into enterprise systems
Implement Retrieval-Augmented Generation (RAG) pipelines for knowledge-driven applications
Implement agent-based automation for workflow execution and decision support
Integrate LLM services (Azure OpenAI, OpenAI, Anthropic, etc.) into Java-based microservices using secure, scalable patterns
Build and orchestrate multi-step GenAI workflows using LangChain (via Java/Python interoperability or service-based architecture)
Build and orchestrate multi-step GenAI workflows using custom Java-based orchestration layers and state machines
Design and manage tool calling and agent execution frameworks
Design and manage context, memory, and prompt lifecycle management
Design and manage conditional routing, fallback logic, retries, and resilience mechanisms
Ensure workflows are robust, observable, and production-ready at scale
Develop and deploy services on cloud platforms (Azure preferred) using containers (Docker) and orchestration (Kubernetes / AKS)
Develop and deploy services on cloud platforms (Azure preferred) using managed cloud services for AI, messaging, storage, and security
Build and maintain CI/CD pipelines using tools such as GitHub Actions / Azure DevOps / Jenkins
Build and maintain CI/CD pipelines with automated build, test, security scan, and deployment stages
Apply Infrastructure as Code principles using Terraform, Bicep, or ARM templates
Ensure high availability, scalability, and cost efficiency of GenAI services
Write clean, maintainable, and testable Java code adhering to SOLID and clean architecture principles
Implement unit, integration, and contract tests
Implement API and workflow-level automated testing
Monitor and enforce code quality, security, and compliance standards
Monitor and enforce logging, metrics, and distributed tracing for GenAI services
Participate in code reviews, design discussions, and architecture governance