> Markdown version of [/jobs/ext/3995798-java-ai-developer](https://www.wearedevelopers.com/jobs/ext/3995798-java-ai-developer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Java-AI developer

- **Company:** Marlabs, Inc
- **Location:** ENGLEWD CLFS, NJ, United States
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** Java (Programming Language), Spring Security, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Applications Architecture, Microsoft Azure, Encodings, Databases, Information Retrieval, Java Persistence API, Python (Programming Language), Meta-Data Management, OpenAI, Search Technologies, Systems Integration, Data Logging, Enterprise Software Applications, Retrieval-Augmented Generation, Large Language Models, Prompt Engineering, Spring-boot, Software Application Programming, Generative AI, Indexer, Backend, Fastapi, Spring Data, Containerization, AI Platforms, Claude, Google Gemini, Restful APIs, Docker, Microservices
- **Published:** October 28, 2026
- **Apply:** https://www.dice.com/job-detail/32d948aa-345a-48fe-811c-0e42a9baab3e

## About the Role

The ideal candidate is fundamentally a strong Java/Spring Boot/Microservices engineer who has transitioned into hands-on GenAI engineering, rather than someone with only data-science or prompt-engineering experience., Java / Backend Engineering

 * Strong hands-on experience with Java
 * Strong expertise in Spring Boot
 * Hands-on experience designing and developing Microservices
 * RESTful API development
 * Spring Security
 * Spring Data / JPA
 * API integration and backend system design
 * Understanding of scalable and distributed application architecture

Generative AI / LLM

 * Hands-on experience developing applications using Large Language Models (LLMs)
 * Strong understanding of Generative AI application architecture
 * Experience working with platforms/models such as:

 * Azure OpenAI / OpenAI
 * AWS Bedrock
 * Llama
 * Claude
 * Gemini

Strong understanding of Prompt Engineering

LLM response evaluation and optimization

Experience integrating LLMs with enterprise applications

Your previous GenAI JD similarly identifies OpenAI, Azure OpenAI, Claude, Gemini and Llama as relevant LLM experience.

RAG

 * Strong hands-on experience designing and implementing Retrieval-Augmented Generation (RAG) solutions.
 * Document ingestion and preprocessing
 * Chunking strategies
 * Embedding generation
 * Semantic search
 * Context retrieval
 * Reranking
 * Prompt/context construction
 * RAG quality evaluation and optimization

## Description

Primary Stack: Java, Spring Boot, Microservices, GenAI, LLM, RAG, Vector Databases, Python, FastAPI

Must Have:
Java | Spring Boot | Microservices | GenAI | LLM | RAG | Vector Database | Python | FastAPI | REST APIs, * Extensive experience (8+ years) with "Microservice Java" development and customization

 * Design and develop scalable backend applications using Java, Spring Boot, and Microservices architecture.
 * Design and implement GenAI applications leveraging LLMs.
 * Build production-grade RAG pipelines for enterprise knowledge retrieval and question-answering use cases.
 * Integrate LLM capabilities into existing Java/Spring Boot enterprise applications.
 * Develop AI services and orchestration components using Python and FastAPI.
 * Design REST APIs and microservices for communication between enterprise applications and AI services.
 * Implement embedding, indexing, semantic search, retrieval, reranking, and response-generation workflows.
 * Implement and optimize Vector Databases for semantic search and enterprise knowledge retrieval.
 * Develop document ingestion, chunking, embedding, metadata management, and retrieval pipelines.
 * Apply prompt engineering techniques to improve LLM response quality and reliability.
 * Develop reusable components for LLM integration, RAG, prompt management, and AI service integration.
 * Implement appropriate authentication, authorization, security, logging, exception handling, and observability across APIs and microservices.
 * Containerize and deploy applications using Docker and CI/CD pipelines.
 * Collaborate with architects, developers, data engineers, and business teams to translate requirements into production-ready GenAI solutions.