TECHNICAL LEAD - FullStack-Java

Full Stack Developer Java (Primary) | React.js (Secondary) | Agentic AI

Experience: 8+ Years Primary Skill: Java (Spring Boot / Netflix DGS) Secondary Skill: React.js (TypeScript) Focus Area: Agentic AI / LLM-powered Systems

About the Role

We are looking for an experienced Full Stack Developer with a strong foundation in Java backend engineering and working proficiency in React.js, who is excited to build next-generation Agentic AI systems. You will design and develop enterprise-grade backend services while also contributing to front-end experiences that bring AI-driven workflows, multi-agent interactions, and real-time LLM outputs to life.

This role is ideal for a full stack engineer who wants to go beyond traditional CRUD applications and work at the intersection of scalable backend architecture, modern front-end engineering, and applied AI.

Key Responsibilities

Backend Development (Java Primary)

• Design and build scalable backend services using Java (Spring Boot / Netflix DGS) for enterprise integrations and high-throughput APIs.
• Integrate AI agents and LLM-powered workflows with enterprise systems via REST APIs, event streams, and databases.
• Design and implement tool integrations that allow AI agents to interact with internal services, APIs, and automation workflows.
• Build and maintain AI microservices (Python/FastAPI where applicable) to expose agent capabilities to downstream consumers.
• Implement memory architectures for AI agents, including short-term memory, long-term knowledge retrieval, and context management.
• Design observability, monitoring, and evaluation frameworks to track LLM performance, agent behavior, hallucination rates, and task success.
• Build guardrails and safety mechanisms to ensure reliable, governed AI system behavior.
• Design, develop, and deploy services on Microsoft Azure, leveraging Azure OpenAI, Azure Functions, Azure Kubernetes Service (AKS), and related cloud services.

Frontend Development (React.js Secondary)

• Develop modern, scalable front-end applications using React and TypeScript to deliver intuitive interfaces for AI-driven workflows, multi-agent interactions, and task orchestration dashboards.
• Implement real-time response handling streaming chat responses, token-by-token updates, agent tool traces, and live execution timelines using WebSocket, Socket.IO, or Server-Sent Events (SSE).
• Build front-end components that visualize agentic AI systems, including reasoning steps, tool invocations, and planning timelines.
• Implement 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, and semantic matches.
• Integrate backend AI services via REST, GraphQL, WebSocket, and streaming endpoints.
• Manage application state using Redux Toolkit, Zustand, or React Query, optimized for real-time, high-frequency AI data flows.
• Apply front-end performance optimizations lazy loading, Suspense, memoization, virtualization, and streaming-friendly rendering.
• Secure front-end applications with best practices around XSS protection, content sanitization, secure storage, authentication flows, and CSP headers.
• Write comprehensive tests using Jest and React Testing Library, including for streaming interactions and agent workflows.

Agentic AI / LLM Engineering

• 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 for semantic search and knowledge retrieval.
• Optimize prompt engineering, model selection, token usage, latency, and cost efficiency.
• Design and run evaluation and experimentation pipelines to continuously improve agent accuracy, reliability, and performance.
• Collaborate with product managers and engineering teams to translate business problems into AI-driven solutions.

Required Skills & Experience

• 8+ years of professional software development experience, with strong expertise in Java (Spring Boot / Netflix DGS).
• Working proficiency in React.js and TypeScript for building production-grade front-end applications.
• Hands-on experience building or integrating Agentic AI / LLM-based systems.
• Experience with LLM APIs (OpenAI, Azure OpenAI) and agent orchestration frameworks (LangChain, LangGraph, LlamaIndex).
• Experience building RAG pipelines and working with vector databases (PgVector, Pinecone, Weaviate, or Milvus).
• Strong Python skills with Object-Oriented design principles for LLM orchestration and prompt engineering; experience with FastAPI.
• Experience with real-time data handling (WebSocket, SSE, Socket.IO) on the front end.
• Familiarity with state management libraries (Redux Toolkit, Zustand, React Query).
• Experience with Microsoft Azure services (Azure OpenAI, Azure Functions, AKS, Azure AD authentication).
• Solid understanding of front-end security practices (XSS protection, CSP, secure storage, auth flows).
• Experience with testing frameworks such as Jest and React Testing Library.
• Strong communication and collaboration skills to work across product and engineering teams.

Nice to Have

• Experience designing observability/evaluation frameworks for LLM or agent-based systems.
• Experience building reusable design systems / component libraries using Atomic Design principles.
• Exposure to GraphQL-based integrations.
• Experience implementing guardrails, content moderation, and AI governance UX patterns.