Java Fullstack Agentic AI Programmer

Job Description

Job Title: Java Full Stack Lead (Java, React, and Agentic AI)
Experience: 8 to 12 Years

Location : Bangalore/Noida/Hyderabad/Pune

NP: Immediate Joiner or Serving who can join us within 15 days

Mandatory Skills: JAVA, Spring boot, Microservices, Kafka, Design Patterns, React,  AI Agent orchestration (LangChain, LangGraph), LLM systems, RAG, Vector Databases (PgVector), Python, FAST API, Azure

Key Responsibilities:

• Design and develop Agentic AI systems capable of reasoning, planning, and executing complex workflows using Large Language Models.
• Build AI-powered services using LLM APIs such as OpenAI, Azure OpenAI Service, or other foundation model providers.
• Develop and orchestrate AI agents using frameworks such as LangChain, LangGraph, and LlamaIndex.
• Design and implement multi-agent systems, including agent collaboration, task decomposition, and tool usage.
• Build Retrieval-Augmented Generation (RAG) pipelines integrating enterprise knowledge sources.
• Integrate vector databases such as PgVector, Pinecone, Weaviate, or Milvus to enable semantic search and knowledge retrieval.
• Build scalable backend services using Java (Spring Boot / Netflix DGS) for enterprise integrations and high-throughput APIs.
• Write Python services using Object-Oriented design principles to support LLM orchestration, prompt engineering, and agent execution.
• Develop AI microservices using FastAPI to expose agent capabilities and LLM-powered workflows.
• Integrate AI agents with enterprise systems via REST APIs, event streams, and databases.
• Design and implement tool integrations enabling AI agents to interact with internal services, APIs, and automation workflows.
• Implement memory architectures for AI agents including short-term memory, long-term knowledge retrieval, and context management.
• Design observability, monitoring, and evaluation frameworks to measure LLM performance, agent behaviour, hallucination rates, and task success.
• Optimize prompt engineering, model selection, token usage, latency, and cost efficiency.
• Build guardrails and safety mechanisms for reliable AI system behaviour.
• Design, develop, and deploy AI services on Microsoft Azure, leveraging services such as Azure OpenAI, Azure Functions, Azure Kubernetes Service (AKS), and related cloud services.
• Design and run evaluation pipelines and experimentation frameworks to continuously improve AI agent accuracy, reliability, and performance.
• Collaborate with product managers, and engineering teams to translate business problems into AI-driven solutions.

Required Skills

• Design and develop modern, scalable front-end applications using React and TypeScript, delivering intuitive interfaces for AI-driven workflows, multi-agent interactions, and complex task orchestration dashboards.
• Real-time Response handling as streaming chat responses, token-by-token updates, agent tool traces, and live execution timelines- using WebSocket, Socket.IO or Server-Sent Events (SSE).
• Develop front-end components that visualize agentic AI systems, including reasoning steps, tool invocations, graphs and planning timelines.
• Implement advanced chat UI patterns for LLM experiences: markdown rendering, citations, code blocks, memory visualizers, context inspectors, and interactive prompt builders.
• Build RAG-aware UI components that highlight retrieved chunks, knowledge sources, confidence scores, semantic matches, and dynamic grounding of answers.
• Integration of backend AI services via REST, GraphQL, WebSocket, and streaming endpoints to support complex workflows, agent execution states, and continuous output rendering.
• Develop state management architecture using Redux Toolkit, Zustand or React Query, optimized for real-time data flows and high-frequency updates from AI systems.
• Implement front-end performance optimizations including lazy loading, Suspense, memorization, virtualization, and streaming-friendly rendering strategies to support low-latency AI UX.
• Build reusable design systems and UI component libraries based on Atomic design patterns.
• Secure the front-end application with best practices around XSS protection, content sanitization, secure storage, authentication flows, and CSP headers.
• Implement guardrails and safety UX patterns (content moderation messages, blocked actions, restricted inputs, fallback UIs) aligned with enterprise AI governance.
• Perform comprehensive testing …