Job Description

WNS, part of Capgemini, is an Agentic AI-powered leader in intelligent operations and transformation, serving more than 700 clients across 10 industries, including Banking and Financial Services, Healthcare, Insurance, Shipping and Logistics, and Travel and Hospitality. We bring together deep domain excellence – WNS’ core differentiator – with AI-powered platforms and analytics to help businesses innovate, scale, adapt and build resilience in a world defined by disruption.Our purpose is clear: to enable lasting business value by designing intelligent, human-led solutions that deliver sustainable outcomes and a differentiated impact. With three global headquarters across four continents, operations in 13 countries, 65 delivery centers and more than 66,000 employees, WNS combines scale, expertise and execution to create meaningful, measurable impact.

Group / Deputy Manager | AI Engineering – Conversational AI & Data Products (6–12 Years)

`

Function Overview

The AI Engineering function is focused on building next-generation conversational AI platforms that enable natural language interaction with enterprise data products for global pharmaceutical organizations. The team develops scalable AI systems that sit on top of commercial analytics data, enabling business users to query, explore, and derive insights through LLM-powered conversational interfaces.

This function partners closely with Commercial Analytics, Data Engineering, Product, and Business stakeholders to transform traditional dashboards into AI-native, decision intelligence systems.

The role sits within the Conversational AI & Data Products team, responsible for designing and deploying LLM-driven interfaces, retrieval systems, and AI agents that interact with governed enterprise data.

Roles and Responsibilities

• Design and develop conversational AI systems that enable natural language access to commercial analytics data products
• Build and deploy LLM-powered pipelines (RAG, agents, copilots) for querying structured and semi-structured enterprise data
• Translate business questions into AI workflows (e.g., KPI retrieval, root-cause analysis, anomaly explanation, trend summarization)
• Develop semantic-aware retrieval layers integrating data warehouses (e.g., Snowflake, Databricks) with LLMs
• Engineer prompt frameworks, embeddings, and context management pipelines to improve response accuracy and grounding
• Implement NL-to-SQL / NL-to-metrics translation systems aligned with governed semantic layers
• Collaborate with Data Engineering and BI teams to ensure AI readiness of data products (metadata, lineage, KPI logic, ontologies)
• Build multi-turn conversational agents supporting follow-ups, drill-downs, and contextual reasoning
• Develop automated narrative generation systems for KPI insights and business storytelling
• Design and implement evaluation frameworks for LLM outputs (accuracy, hallucination control, explainability)
• Ensure solutions are scalable, secure, and compliant with enterprise governance and data privacy standards
• Optimize performance and cost of LLM systems (latency, token usage, caching strategies)
• Partner with product and business teams to identify and prioritize high-impact AI use cases
• Contribute to platform architecture, reusable components, and internal AI frameworks
• Mentor junior team members and contribute to AI engineering best practices

Core Competencies

Technical Skills

• Strong experience in LLM application development (e.g., GPT-based systems, open-source LLMs)
• Hands-on with RAG (Retrieval-Augmented Generation), vector databases, and embeddings
• Experience building NL-to-SQL / semantic query systems
• Proficiency in Python (preferred) and/or backend engineering (APIs, microservices)
• Experience with LangChain, LlamaIndex, or similar orchestration frameworks
• Familiarity with Databricks, Snowflake, or modern data platforms
• Strong SQL skills and understanding of analytical data modeling
• Knowledge of semantic layers, ontologies, and KPI frameworks
• Experience with API integration and scalable AI system deployment (cloud: AWS/Azure/GCP)
• Understanding of LLM evaluation, guardrails, prompt engineering, and hallucination mitigation

Domain & Functional Knowledge

• Familiarity with enterprise data products and BI ecosystems
• Ability to translate business questions into AI-driven analytical workflows
• Understanding of data governance, lineage, and compliance requirements

Behavioral & Professional Skills

• Strong problem-solving with a systems-thinking mindset
• Ability to work across AI, data engineering, and business teams
• Strong communication skills to explain AI system behavior and limitations
• Ownership mindset with ability to drive end-to-end AI solutions
• Adaptability to rapidly evolving LLM and AI ecosystems
• Focus on quality, scalability, and user-centric design

Must-Have Skills

• Experience building LLM-based applications (RAG, copilots, or agents)
• Strong Python + SQL skills
• Hands-on experience with vector databases and embeddings
• Understanding of semantic data models and KPI-driven analytics
• Experience integrating AI with enterprise data platforms
• Strong communication and documentation skills

Good-to-Have Skills

• Experience with NL-to-SQL or conversational BI systems
• Exposure to multi-agent systems or autonomous AI workflows
• Familiarity with Databricks, MLflow, or AI notebooks
• Experience in pharma or healthcare analytics
• Knowledge of model fine-tuning, LoRA, or domain adaptation
• Exposure to AI explainability frameworks and governance

Education

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, Engineering, or related field
• Strong foundation in machine learning, NLP, or distributed systems

Qualifications

Preferred QualificationsExperience with cloud platforms such as AWS, Azure, or GCP.Knowledge of MLOps, CI/CD pipelines, and containerization tools like Docker/Kubernetes.Familiarity with databases, vector databases, and data engineering workflows.Exposure to LLMs, NLP, or Generative AI frameworks is a plus.Educational QualificationBE / BTech / MCA / MTech in Computer Science, Engineering, or a related field.