New opportunity

Full Stack developer

NetApp · Bangalore, India

About this role

The Full Stack Developer will lead the design, development, implementation, and support of enterprise-scale AI and Large Language Model (LLM) solutions, alongside custom full-stack applications to drive innovation and operational efficiency across HR, Legal, and Finance functions. Key responsibilities include integrating AI/LLM solutions with HR, Finance, and DevOps platforms, developing custom applications with modern full-stack technologies, and communicating project milestones to senior management. Candidates must proactively manage project risks and collaborate with cross-functional stakeholders. Required qualifications include a B.E/B.Tech or Masters in Computer Science with at least 8 years of related experience. Technical requirements include proficiency in front-end frameworks (React, Angular, or Vue.js), back-end languages (Java, Python, Ruby, or Node.js), and cloud services. Specialized AI/LLM expertise is required in Generative AI, RAG, Prompt Engineering, vector databases, and document ingestion/retrieval workflows. Knowledge of HR/Finance business scenarios (SAP Successfactors, Oracle ERP) and integration tools is preferred. The role operates in a hybrid work environment.

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

Skills for this role

HTMLCSSJavaScriptReactAngularVue.jsJavaPythonRubyNode.jsMySQLPostgreSQLMongoDBCI/CDGitAWSAzureGoogle Cloud PlatformGenerative AIRAGPrompt EngineeringLLMsMicrosoft Graph APISharePoint OnlineAzure ADEntra IDWeaviateAzure AI SearchOAuth 2.0REST APIs

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

Enterprise AI and LLM Solution Delivery
The primary focus is designing and implementing end-to-end AI solutions, specifically utilizing RAG, prompt engineering, and vector databases. You must demonstrate the ability to manage the full lifecycle of document ingestion, chunking, embedding, and retrieval workflows while optimizing for accuracy and hallucination detection.
Full-Stack Application Development for Business Functions
You are expected to build and maintain custom applications that support HR, Legal, and Finance operations. This requires proficiency in modern front-end frameworks (React, Angular, or Vue.js) and back-end languages (Java, Python, Ruby, or Node.js) to ensure scalable and reliable business tools.
Cross-Functional Stakeholder Management
Success in this role depends on your ability to communicate project milestones and business outcomes to senior management. You must proactively identify and resolve project risks and bottlenecks by collaborating effectively across diverse business units.
Integration with Enterprise Platforms
You must integrate AI and custom applications with existing enterprise ecosystems, including Microsoft Graph API, SharePoint, and potentially SAP Successfactors or Oracle ERP. This requires a strong grasp of OAuth 2.0, security trimming, and RBAC to ensure secure data access.

Likely challenges to think through

Balancing AI Innovation with Enterprise Security
Implementing Generative AI in sensitive HR and Finance domains introduces significant security and compliance risks. Prepare to discuss how you handle data privacy, security trimming, and access control (RBAC) when building LLM-based retrieval systems.
Optimizing RAG Performance for Business Accuracy
Moving beyond basic RAG implementations to production-grade systems requires rigorous optimization of retrieval, reranking, and citation generation. Be ready to explain your methodology for minimizing hallucinations and ensuring the reliability of AI-generated responses in a corporate context.
Navigating Complex Legacy Integrations
Integrating modern AI solutions with established ERP systems like SAP or Oracle can be technically challenging due to proprietary APIs and rigid data structures. Prepare to discuss your experience with middleware, REST/SOAP APIs, and integration tools to bridge the gap between legacy data and modern AI interfaces.

Practice your answers

Technical practice

Designing RAG Workflows

What to coverExplain the end-to-end architecture of a Retrieval-Augmented Generation (RAG) pipeline. Focus on document ingestion, chunking strategies, embedding generation, and how you optimize retrieval accuracy and citation generation.

Vector Database Selection and Optimization

What to coverCompare different vector databases like Weaviate or Azure AI Search. Discuss how you handle indexing, search performance, and scaling for enterprise-scale AI solutions.

Prompt Engineering and Hallucination Mitigation

What to coverDescribe your approach to prompt engineering for enterprise applications. Explain specific techniques you use to ground LLM responses in provided data and how you implement automated hallucination detection.

Full-Stack Security and Authentication

What to coverHow do you implement OAuth 2.0 and RBAC in a full-stack application? Explain how you manage access tokens and security trimming when integrating with Microsoft Graph API or SharePoint.

Integrating AI with Enterprise Platforms

What to coverDiscuss the challenges of integrating AI/LLM solutions with existing HR or Finance systems like SAP Successfactors or Oracle ERP. Address how you handle data synchronization and API-based communication.

Scalable Full-Stack Development

What to coverDescribe your process for building scalable applications using modern front-end frameworks (React/Angular/Vue) and back-end services. How do you ensure reliability and maintainability in a production environment?

CI/CD and Cloud Deployment

What to coverExplain your experience with CI/CD pipelines and cloud services (AWS/Azure/GCP). How do you automate testing and deployment for complex applications that include AI components?

Workflow Automation Tools

What to coverDiscuss your experience with workflow automation tools like n8n or Co-pilot studio. Provide an example of how you have used these to improve operational efficiency in a business function.

Behavioural practice

Managing Project Risks

What to coverDescribe a situation where you identified a significant project risk or bottleneck. Explain the steps you took to escalate the issue and how you collaborated with stakeholders to implement a solution.

Communicating Technical Concepts to Non-Technical Stakeholders

What to coverProvide an example of how you have communicated project milestones and business outcomes to senior management. How do you ensure that technical complexity does not obscure the business value?

Cross-Functional Collaboration

What to coverTell me about a time you had to work with cross-functional teams (e.g., HR, Legal, or Finance) to deliver a technical solution. How did you align their business requirements with your technical implementation?

Handling Changing Requirements

What to coverDescribe a project where requirements shifted mid-development. How did you manage the impact on your team's workload while ensuring the final product remained aligned with business goals?

Sharpen your knowledge

Topics to prepare

RAG and LLM Retrieval Workflows
Focus on the end-to-end lifecycle of RAG systems, specifically document ingestion, chunking strategies, embedding models, and retrieval optimization. Practice designing workflows that include reranking and hallucination detection to ensure high-quality, grounded responses for enterprise applications.
Enterprise Security and Identity Integration
Review the implementation of OAuth 2.0, RBAC, and security trimming within AI applications. Understand how to integrate Microsoft Graph API and Azure AD/Entra ID to ensure that AI-driven solutions respect existing enterprise data permissions and access controls.
Business Domain Integration
Study the integration of custom applications with HR and Finance platforms like SAP Successfactors and Oracle ERP. Focus on how to leverage REST/SOAP APIs to bridge the gap between custom AI solutions and established enterprise business systems.

Skills to revise

Vector Database Management
Gain hands-on experience with vector databases such as Weaviate or Azure AI Search. Practice indexing, querying, and managing vector embeddings to support efficient retrieval in large-scale AI solutions.
Prompt Engineering and Optimization
Develop advanced prompt engineering techniques to improve model performance. Practice creating structured prompts that minimize hallucinations and maximize the relevance of citations in enterprise-scale LLM outputs.
Full Stack Development with Modern Frameworks
Ensure proficiency in building scalable front-end interfaces using React, Angular, or Vue.js, paired with robust back-end services in Python or Node.js. Focus on creating secure, API-driven architectures that support enterprise-scale deployments.

Your preparation checklist

Architect an RAG-based document retrieval workflow
Prepare a technical walkthrough of a RAG pipeline you have built. Focus on document ingestion, chunking strategies, embedding models, and vector database selection (e.g., Weaviate or Azure AI Search). Be ready to explain how you optimized retrieval accuracy, handled reranking, and implemented hallucination detection.
Map full-stack expertise to enterprise integrations
Review your experience integrating front-end frameworks (React/Angular/Vue) with back-end services (Java/Python/Node.js) and cloud platforms. Prepare to discuss how you have secured these applications using OAuth 2.0, RBAC, and Azure AD/Entra ID, specifically in the context of connecting to enterprise systems like SAP Successfactors or Oracle ERP.
Prepare evidence of cross-functional project leadership
Draft specific examples of how you have communicated complex technical milestones to senior management. Identify a time you proactively managed a project risk or bottleneck and describe the collaborative steps you took with stakeholders to resolve it.
Formulate strategic questions for the hiring team
Prepare thoughtful questions regarding the current AI/LLM roadmap at NetApp, such as: 'How does the team currently balance the use of off-the-shelf LLM services versus custom-trained models for HR and Finance workflows?' or 'What are the primary challenges you face when integrating AI solutions with legacy ERP systems like SAP or Oracle?'

Availability has not yet been verified. 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…