Java Full Stack Developer – AI Applications

Zoho; Bengaluru; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Zoho in Bengaluru seeks a Java Full Stack Developer focused on AI applications to design, build, and deploy scalable AI-driven solutions. You will integrate LLMs and data pipelines into core business platforms.

You will work across Java, Python, TypeScript, and Node.js to implement Retrieval-Augmented Generation pipelines, vector databases with pgvector, and AI orchestration frameworks, collaborating with cross-functional teams to deliver robust, secure features.

Qualifications

• 6–8 years of professional software development experience in IT services.
• Strong Java full-stack skills plus Python and TypeScript.
• Hands-on Node.js for backend services and API development.
• Experience with LangChain, LlamaIndex, or Semantic Kernel.
• Experience with PostgreSQL and vector extensions like pgvector.
• Understanding API design and event streaming patterns.
• Familiarity with RAG architectures and various LLMs/APIs.

Responsibilities

• Architect and develop full-stack applications using Java, Python, TypeScript, and Node.js for AI workflows.
• Design and implement RAG pipelines to improve intelligence and data retrieval.
• Integrate APIs and event streaming between legacy systems and AI services.
• Build and optimize vector databases with PostgreSQL and pgvector.
• Develop LLM orchestration frameworks with LangChain, LlamaIndex, or Semantic Kernel.
• Collaborate with teams to translate business needs into AI features.
• Ensure security, scalability, and performance of AI components.

Skills

Java Full-Stack

Python

TypeScript

Node.js

AI/LLM

RAG architectures

PostgreSQL

pgvector

LangChain

API design

Security

Tools

LangChain

LlamaIndex

Semantic Kernel

pgvector

Job description

Java Full Stack Developer – AI Applications

Job Description

Summary

We are seeking a highly skilled Java Full Stack Developer with a specialized focus on Artificial Intelligence applications to join our IT Services team. In this pivotal role, you will leverage your extensive background in full-stack engineering to design, build, and deploy scalable AI-driven solutions. You will bridge the gap between traditional enterprise software architecture and cutting-edge generative AI technologies, ensuring robust integration of Large Language Models (LLMs) and advanced data processing pipelines into our core business platforms.

Responsibilities

• Architect and develop full-stack applications using Java, Python, TypeScript, and Node.js to support complex AI workflows.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines to enhance application intelligence and data retrieval accuracy.
• Integrate enterprise-grade APIs and event streaming mechanisms to facilitate real-time data flow between legacy systems and modern AI services.
• Build and optimize vector databases using PostgreSQL and pgvector for efficient semantic search and knowledge management.
• Develop and maintain LLM orchestration frameworks utilizing tools such as LangChain, LlamaIndex, or Semantic Kernel.
• Collaborate with cross-functional teams to translate business requirements into technical specifications for AI-powered features.
• Ensure the security, scalability, and performance of all AI components within the application ecosystem.

Requirements

Requirements:

• Possess 6 to 8 years of professional software development experience within the IT Services sector.
• Demonstrate strong proficiency in Java full-stack development alongside modern scripting languages like Python and TypeScript.
• Have hands‑on experience with Node.js for backend services and API development.
• Show proven expertise in working with LangChain, LlamaIndex, or Semantic Kernel for AI application logic.
• Be skilled in managing relational databases, specifically PostgreSQL, with a focus on vector extensions like pgvector.
• Understand the principles of Enterprise API design and event stream integration patterns.
• Possess a solid grasp of RAG architectures and the ability to interact with various LLMs and AI APIs.
• Hold a competitive compensation package aligned with market standards for this level of expertise.