New opportunity

Z2_AI Java/Python

NTTD Info Pro Ser Pte Ltd · Bangalore, India

About this role

NTT DATA is seeking a Z2_AI Java/Python professional to join their team in Bangalore, India. This role focuses on the end-to-end development of AI products, including ideation, prototyping, deployment, and maintenance. Responsibilities include building AI applications, chatbots, and multi-agent systems, developing LLM RAG pipelines, and designing AI orchestration layers or MCP servers for enterprise integration. The role also involves leading the migration of legacy systems to microservices and AI-enabled solutions. Required qualifications include strong proficiency in Java, Spring Boot, and microservices, alongside frontend development experience with Vue.js, React, or Angular. Candidates must have experience with Python and AI/ML frameworks such as PyTorch or TensorFlow, as well as practical knowledge of chatbots, AI agents, LLM prompt engineering, RAG, API integration, and distributed systems. Familiarity with DevOps practices and tools like Git, GitHub Actions, and GitLab CI is required. Preferred technical skills include experience with LangChain, LlamaIndex, Semantic Kernel, vector databases (Pinecone, FAISS), Kafka, Spark, Kubernetes, Docker, Azure OpenAI, AWS Bedrock, and Camunda for workflow management.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

JavaPythonSpring BootMicroservicesVue.jsReactAngularPyTorchTensorFlowChatbotsAI AgentsLLMPrompt EngineeringRAGAPI IntegrationDistributed SystemsDevOpsGitGitHub ActionsGitLab CILangChainLlamaIndexSemantic KernelPineconeFAISSKafkaSparkKubernetesDockerAzure OpenAI

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

End-to-End AI Product Lifecycle Management
The role requires ownership of the entire development lifecycle, from initial ideation and prototyping to deployment and ongoing maintenance. You must demonstrate the ability to manage technical decisions across the full stack while ensuring AI applications remain performant and scalable in production.
Hybrid Java and Python Integration
You must bridge the gap between traditional enterprise backend systems (Java, Spring Boot, Microservices) and modern AI/ML workflows (Python, PyTorch, TensorFlow). Success depends on your ability to integrate these distinct environments into cohesive, functional AI-enabled solutions.
Enterprise AI Orchestration and RAG Implementation
A core priority is designing AI orchestration layers and LLM RAG pipelines. You will be expected to utilize frameworks like LangChain or LlamaIndex to connect enterprise data with AI models, ensuring secure and efficient information retrieval and agentic behavior.
Legacy System Modernization
The role involves leading the migration of legacy systems to microservices and AI-enabled architectures. You must be prepared to refactor existing codebases while simultaneously introducing modern AI capabilities, often utilizing tools like Camunda for workflow management.

Likely challenges to think through

Balancing Diverse Technical Stacks
The requirement to be proficient in both Java/Spring Boot and Python/AI frameworks creates a high cognitive load. Prepare by highlighting specific projects where you successfully maintained high-performance backend services while simultaneously deploying machine learning models.
Complexity of Multi-Agent System Design
Developing multi-agent systems and MCP servers involves significant architectural complexity regarding state management and inter-agent communication. Be ready to discuss how you handle distributed system challenges and ensure reliability when agents interact with external APIs.
Maintaining Production-Grade AI
Moving AI from prototype to production is difficult due to non-deterministic model outputs and data drift. Prepare by discussing your experience with DevOps practices (Git, CI/CD) and how you implement monitoring and maintenance strategies for AI services.

Practice your answers

Technical practice

Designing AI Orchestration Layers

What to coverExplain your approach to designing an orchestration layer for enterprise AI integration. Focus on how you manage state, handle multi-agent communication, and ensure scalability when integrating with LLMs like Azure OpenAI or AWS Bedrock.

Implementing RAG Pipelines

What to coverDescribe the architecture of a robust RAG pipeline you have built. Discuss your choice of vector databases (e.g., Pinecone or FAISS), strategies for document chunking, and how you optimize retrieval accuracy for LLM generation.

Microservices Migration Strategy

What to coverWhen leading the migration of a legacy system to microservices, how do you ensure zero-downtime and data consistency? Suggestion: Prepare to discuss the use of tools like Camunda for managing complex workflows during the transition.

Java and Python Interoperability

What to coverThis role requires both Java/Spring Boot and Python/AI frameworks. Explain how you architect systems that leverage Java for robust backend services while utilizing Python for AI/ML model execution and data processing.

AI Agent Development

What to coverWhat are the key challenges in building multi-agent systems? Discuss how you handle agent autonomy, task delegation, and error handling when using frameworks like LangChain or Semantic Kernel.

DevOps for AI Products

What to coverHow do you integrate AI model deployment into a CI/CD pipeline using GitHub Actions or GitLab CI? Address the specific challenges of versioning models, managing containerized environments with Docker/Kubernetes, and monitoring performance.

Prompt Engineering Best Practices

What to coverHow do you approach prompt engineering to ensure consistent and reliable outputs from LLMs in an enterprise context? Discuss techniques like few-shot prompting, chain-of-thought, and how you validate prompt effectiveness.

Distributed Systems and Kafka

What to coverExplain how you use Kafka to handle asynchronous communication in a distributed AI application. Focus on scenarios where high-throughput data ingestion is required for real-time AI processing.

Behavioural practice

End-to-End Product Ownership

What to coverDescribe a time you owned an AI product from ideation to deployment. Focus on how you balanced technical requirements with business goals and managed stakeholders throughout the lifecycle.

Adapting to New AI Frameworks

What to coverThe AI field evolves rapidly. Provide an example of how you quickly learned and implemented a new tool or framework (e.g., LlamaIndex or a new vector database) to solve a specific project challenge.

Handling Technical Debt during Migration

What to coverTell me about a situation where you had to migrate a legacy system while simultaneously introducing new AI features. How did you prioritize technical debt versus new feature delivery?

Cross-Functional Collaboration

What to coverDescribe a scenario where you had to explain complex AI/ML concepts to non-technical team members or clients. How did you ensure alignment on the project's feasibility and limitations?

Sharpen your knowledge

Topics to prepare

LLM RAG Pipeline Architecture
Review the conceptual flow of Retrieval-Augmented Generation, specifically how data is ingested, indexed in vector databases, and retrieved to augment LLM prompts. Exercise: Sketch a high-level diagram showing the integration of a vector database (like Pinecone or FAISS) with an LLM service (Azure OpenAI or AWS Bedrock) to solve a specific enterprise knowledge retrieval problem.
AI Orchestration and Multi-Agent Systems
Understand the design patterns for AI orchestration layers and multi-agent systems, including how agents communicate and delegate tasks. Exercise: Research the Model Context Protocol (MCP) and define how an orchestration layer would manage state and tool access for a multi-agent chatbot system.
Microservices Migration Strategies
Study patterns for migrating legacy monolithic systems to microservices, focusing on decoupling services and integrating AI-enabled components. Exercise: Outline a phased migration plan for a legacy Java application, identifying which modules are best suited for initial conversion to Spring Boot microservices.

Skills to revise

Java Spring Boot Microservices
Develop a robust backend service using Spring Boot. Exercise: Build a simple RESTful microservice that exposes an API endpoint, which in turn calls an external AI service, ensuring proper error handling and logging for distributed system environments.
Python AI/ML Frameworks
Practice implementing AI models using PyTorch or TensorFlow. Exercise: Create a Python script that uses a pre-trained model to perform a basic NLP task, such as sentiment analysis or text classification, and wrap it in a function that can be called via an API.
Prompt Engineering and LangChain
Master the art of crafting effective prompts and using orchestration frameworks. Exercise: Use LangChain to build a simple chain that takes user input, retrieves relevant context from a mock vector store, and generates a response using a prompt template.

Your preparation checklist

Prepare a technical walkthrough of an AI-enabled microservices project
Develop a concise presentation or code repository demonstrating an end-to-end AI product you have built. Highlight your use of Java/Spring Boot for backend services, Python for AI/ML components, and how you integrated these with a frontend framework like Vue.js or React.
Demonstrate expertise in RAG and AI orchestration
Be ready to discuss your experience building LLM RAG pipelines. Prepare to explain how you have used frameworks like LangChain, LlamaIndex, or Semantic Kernel to manage prompt engineering and AI orchestration layers, specifically referencing how you handled vector databases like Pinecone or FAISS.
Review legacy system migration strategies
Since the role involves leading migrations to microservices and AI-enabled solutions, prepare examples of how you have refactored legacy codebases. Familiarize yourself with Camunda for workflow management, as it is specifically listed as a preferred tool for these migration contexts.
Articulate your DevOps and deployment workflow
Prepare to describe your experience with CI/CD pipelines using GitHub Actions or GitLab CI. Ensure you can explain how you containerize applications with Docker and manage them in Kubernetes environments, as this is critical for the deployment and maintenance responsibilities of the role.
Formulate strategic questions for the interviewers
Prepare thoughtful questions such as: 'How does the team currently balance the development of custom AI orchestration layers versus utilizing managed services like Azure OpenAI or AWS Bedrock?' or 'What are the primary challenges the team faces when integrating multi-agent systems into existing enterprise microservices architectures?'

Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…