Role Overview :
We are looking for a skilled Senior Java Backend Engineer to join our team focused on building scalable and high-performance backend systems for Generative AI applications. You’ll play a key role in designing APIs, orchestrating AI agents, and integrating Large Language Models (LLMs) into production-ready systems. This role is ideal for backend developers with a passion for modern AI technologies and distributed systems.
Key Responsibilities :
- Design, build, and maintain scalable backend services using Java and the Spring Boot framework
- Develop APIs to enable LLM integration and support AI agent orchestration workflows
- Architect microservices to power RAG (Retrieval-Augmented Generation) and other LLM-driven systems
- Optimize performance through efficient caching strategies and vector database interactions
- Integrate and manage connections with multiple LLM providers (e.g., OpenAI, Gemini, Claude), including rate limiting and failover handling
- Implement real-time streaming features for conversational AI systems using WebSockets or similar technologies
- Ensure robust system observability with logging , monitoring , and tracing
Required Skills & Qualifications :
3–7 years total, with a minimum of 1 year working on Generative AI projects
Backend Development :
Minimum 3 years of hands-on experience with Java and Spring BootStrong grasp of RESTful API design principles and microservices architectureProficiency with core Spring modules : Spring Security , Spring Data JPA , Spring CloudExperience working with relational and NoSQL databases : PostgreSQL , MongoDB , RedisFamiliarity with message brokers such as RabbitMQ or Apache KafkaExpertise in caching mechanisms and system performance tuningGenerative AI Integration :
Experience integrating LLM APIs (OpenAI, Gemini, Claude, etc.) into backend servicesKnowledge of vector databases and semantic search technologiesFamiliarity with AI agent orchestration frameworks (e.g., LangGraph )Understanding of RAG systems and how to implement them effectivelyExperience developing streaming responses using WebSockets or server-sent eventsWorking knowledge of prompt templating and management systemsNice to Have :
Experience in fine-tuning LLMs and managing model deployment pipelinesKnowledge of self-hosted LLM environments and infrastructure managementExposure to observability tools like LangSmith or custom monitoring setupsFamiliarity with natural language to SQL systems or BI applications powered by LLMsNote : If you are matching on to the above job description & skills, please feel free to fill in your details on the below Form enclosed (https : / / forms.gle / bUyXMBhgSxxBZVeK9).