Description

You will design and build Java-based microservices integrated with Generative AI frameworks to deliver intelligent enterprise features.

This role is on-site.

Responsibilities

• Develop microservices using Java 8+ and Spring Boot, ensuring scalability and security.
• Implement LLM orchestration workflows using LangChain and LangGraph.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for semantic search.
• Integrate Large Language Models with backend services and vector databases.
• Mentor engineers and lead technical discussions on best practices.

Required Skills

• 5+ years of experience with Java, Spring Boot, and Microservices architecture.
• Hands-on expertise with LangChain/LangGraph for LLM orchestration.
• Deep understanding of RAG pipelines and LLM integration patterns.
• Proficiency with vector databases such as Pinecone, Weaviate, FAISS, or Milvus.
• Experience building RESTful APIs and handling JSON/XML integration.
• Practical knowledge of CI/CD pipelines, Docker, and Kubernetes.
• Strong problem-solving and analytical skills in a distributed system context.

Preferred Skills

• Knowledge of prompt engineering, fine-tuning LLMs, and transformer models (OpenAI, Hugging Face).
• Exposure to data streaming platforms like Kafka or Flink.
• Experience with cloud platforms (AWS, Azure, GCP) for AI/ML services.

Key Skills

Education

Any Graduate