New opportunity

AI Engineer Digital Solutions

WSP · Bengaluru, India

About this role

WSP is seeking an AI Engineer to develop and support production-oriented Generative AI solutions for the Middle East AI portfolio from the Bengaluru GCC. The role focuses on building AI products, agents, and automation workflows with an emphasis on secure engineering, quality, and responsible AI. Responsibilities: Develop GenAI applications, agents, and automation workflows; implement RAG, function calling, and structured outputs; integrate AI components with enterprise systems and vector search services; build data pipelines for ingestion, chunking, and embedding; create evaluation datasets and perform testing for accuracy, safety, and latency; apply responsible AI controls; write clean Python code; and support deployment and monitoring. Qualifications: Bachelor’s degree in Computer Science, Engineering, or Data Science; 3+ years of relevant experience; working knowledge of Python, REST APIs, and SQL; practical understanding of LLMs, RAG, and prompt engineering; exposure to Azure AI services and CI/CD. Preferred: Azure certifications, experience with agentic AI, document intelligence, MLOps, and agile team environments. The role operates under a Hybrid work model.

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

Skills for this role

PythonGenerative AIRAGLLMsPrompt EngineeringAzure OpenAIAzure AI SearchAzure Machine LearningSQLREST APIsGitCI/CDAzure DevOpsVector SearchMicroservices

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

Production-Grade Generative AI Development
The role requires moving beyond prototypes to deliver stable, scalable AI applications. You must demonstrate proficiency in building end-to-end pipelines, including data ingestion, chunking, embedding, and retrieval, while ensuring the final output meets enterprise standards for reliability and latency.
Responsible AI and Security Governance
WSP emphasizes secure engineering and responsible AI. You must be prepared to implement guardrails, content filtering, and traceability mechanisms to ensure AI solutions are safe, compliant with corporate standards, and protected against vulnerabilities like prompt injection or data leakage.
Enterprise Integration and System Architecture
You will be responsible for integrating AI components into existing enterprise systems using REST APIs and microservices. A core priority is ensuring that AI agents and workflows function seamlessly within the broader Azure-based ecosystem, adhering to established architectural and security patterns.
Systematic Evaluation and Quality Assurance
A critical requirement is the creation of evaluation datasets to test for accuracy, grounding, and safety. You must be able to design and execute repeatable testing frameworks that allow for iterative optimization of AI models and workflows.

Likely challenges to think through

Balancing Innovation with Strict Governance
Working within a large consulting firm like WSP involves navigating rigid architecture, security, and delivery governance. The challenge is to innovate with GenAI while strictly adhering to approved technology stacks and compliance processes. Prepare by demonstrating how you have successfully navigated technical constraints in previous projects.
Managing Distributed Stakeholder Expectations
The role involves supporting the Middle East portfolio from a Bengaluru GCC. This requires bridging geographical and cultural gaps while communicating technical progress to non-technical stakeholders. Prepare by highlighting your experience in managing expectations and providing transparent reporting in globally distributed teams.
Maintaining Reliability in Non-Deterministic Systems
GenAI applications are inherently probabilistic, which conflicts with the need for enterprise-grade reliability. The challenge lies in minimizing hallucinations and latency. Prepare by discussing your experience with RAG optimization, prompt engineering techniques, and monitoring strategies to ensure consistent performance in production.

Practice your answers

Technical practice

Implementing RAG Pipelines

What to coverExplain the end-to-end process of building a RAG pipeline, specifically focusing on data ingestion, chunking strategies, and embedding generation. Discuss how you ensure the quality of retrieved context and how you handle potential issues like noise or irrelevant document retrieval.

Function Calling and Structured Outputs

What to coverHow do you implement function calling to enable LLMs to interact with external enterprise systems or APIs? Describe your approach to enforcing structured outputs (e.g., JSON) and ensuring the model adheres to defined schemas for reliable downstream processing.

Evaluating GenAI Solutions

What to coverWhat metrics and methodologies do you use to evaluate the performance of a production-oriented GenAI application? Address how you measure accuracy, grounding, latency, and safety, and explain how you create and maintain evaluation datasets.

Responsible AI and Guardrails

What to coverDescribe the techniques you use to implement responsible AI controls, such as content filtering, prompt guardrails, and human-in-the-loop oversight. How do you ensure traceability and auditability in an enterprise environment?

Azure AI Ecosystem Integration

What to coverGiven the WSP technology stack, how would you leverage Azure AI Search and Azure OpenAI to build a scalable enterprise search solution? Discuss the trade-offs between different indexing strategies and how you manage security within the Azure environment.

Agentic AI Orchestration

What to coverWhat is your experience with agentic AI workflows, and how do you manage state and tool selection in complex, multi-step automation tasks? Discuss how you handle error recovery and loop prevention when agents interact with external APIs.

CI/CD for AI Applications

What to coverHow does the MLOps lifecycle differ from traditional software CI/CD, particularly regarding model versioning and monitoring? Explain how you would set up an automated pipeline for testing and deploying AI components using Azure DevOps.

Python for Enterprise AI

What to coverWhen developing reusable Python components for AI applications, what practices do you follow to ensure code quality, maintainability, and performance? Discuss your approach to handling asynchronous operations when integrating with REST APIs.

Behavioural practice

Collaborating with Distributed Teams

What to coverDescribe a time you worked in a globally distributed team to deliver a technical project. How did you ensure clear communication, manage time zone differences, and maintain alignment with stakeholders in different regions?

Handling Ambiguity in AI Projects

What to coverTell me about a situation where you had to develop an AI solution with evolving or ambiguous requirements. How did you manage the project scope, communicate progress to stakeholders, and ensure the final output met business needs?

Managing Technical Debt and Quality

What to coverDescribe a scenario where you had to balance the need for rapid deployment with the requirement for high-quality, maintainable code. How did you decide what to prioritize, and what steps did you take to ensure long-term system stability?

Problem Solving and Troubleshooting

What to coverGive an example of a complex production issue you encountered in an AI or data-driven system. Walk me through your troubleshooting process, how you identified the root cause, and the steps you took to prevent recurrence.

Sharpen your knowledge

Topics to prepare

Retrieval-Augmented Generation (RAG) Architecture
The role requires implementing RAG pipelines including ingestion, chunking, embedding, and retrieval. Exercise: Design a document processing pipeline that converts unstructured PDFs into vector embeddings stored in a search service, focusing on chunking strategies that maintain context for retrieval accuracy.
Responsible AI and Governance
The position emphasizes secure engineering and responsible AI controls. Exercise: Research and document how to implement content filtering, guardrails, and traceability in an LLM application to ensure safety and human oversight, aligning with enterprise-grade production standards.
Evaluation Frameworks for GenAI
The role involves creating evaluation datasets and testing for latency, accuracy, and safety. Exercise: Develop a test plan that defines metrics for measuring model grounding and response quality, and describe how you would automate these tests within a CI/CD pipeline.

Skills to revise

Python for AI Engineering
The role requires writing clean, reusable Python code for AI components. Exercise: Refactor a script that interacts with an LLM API to include robust error handling, logging, and modular structure suitable for integration into a production microservice.
Azure AI Services Integration
The stack relies on Azure OpenAI and Azure AI Search. Exercise: Create a prototype using the Azure SDK for Python that performs a semantic search query against an Azure AI Search index and uses the results to augment an Azure OpenAI prompt.
CI/CD and MLOps
The role involves supporting deployment and monitoring of AI solutions. Exercise: Outline a CI/CD workflow using Azure DevOps that includes automated unit testing for AI components and a deployment strategy for updating model configurations without downtime.

Your preparation checklist

Review Azure AI service architecture
Familiarize yourself with the WSP technology stack, specifically Azure OpenAI, Azure AI Search, and Azure Machine Learning. Prepare to discuss how you would integrate these services into a production-ready RAG pipeline.
Prepare a RAG project walkthrough
Select a past project involving retrieval-augmented generation. Be ready to explain your approach to data ingestion, chunking strategies, embedding models, and how you ensured retrieval accuracy and latency optimization.
Develop a responsible AI framework
Prepare to explain how you implement guardrails, content filtering, and human-in-the-loop oversight. Have concrete examples of how you have addressed safety and traceability in previous AI deployments.
Demonstrate Python and API proficiency
Review your experience writing clean, modular Python code for REST APIs. Be prepared to discuss how you handle structured outputs and function calling within agentic workflows.
Formulate questions for the interviewer
Prepare thoughtful questions regarding the team's current agile development lifecycle, how they manage MLOps for production monitoring, and the specific nature of the Middle East AI portfolio projects.

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…