Senior Associate – Conversational AI / RAG Engineer

Role Summary : We are looking for a highly skilled Conversational AI / RAG Engineer to design, build, and deploy enterprise-grade conversational AI solutions powered by Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Knowledge Intelligence platforms. The ideal candidate will have hands-on experience building intelligent assistants, enterprise search solutions, knowledge bots, and AI copilots that leverage internal and external data sources to deliver accurate, context-aware responses. This role requires strong expertise in AI engineering, information retrieval, prompt engineering, vector databases, and cloud-native application development.

Key

Responsibilities: Conversational AI Development Design and develop conversational AI applications, virtual assistants, and enterprise copilots. Build multi-turn conversational experiences with contextual memory and personalization. Develop intent-based and GenAI-powered chatbot solutions. Integrate conversational AI solutions with enterprise applications, APIs, and business workflows. Optimize conversation flows, response quality, and user experience. Retrieval-Augmented Generation (RAG) Design and implement end-to-end RAG architectures. Build document ingestion, chunking, embedding, indexing, and retrieval pipelines. Implement semantic search and knowledge retrieval solutions across structured and unstructured data. Optimize retrieval relevance, grounding accuracy, and response quality. Develop scalable enterprise knowledge assistants leveraging internal content repositories. LLM Integration & Prompt Engineering Integrate OpenAI, Azure OpenAI, Gemini, Claude, and open-source models into enterprise applications. Design prompt templates and orchestration workflows. Develop strategies to minimize hallucinations and improve answer fidelity. Conduct prompt tuning and response evaluation to enhance system performance. AI Application Engineering Build AI microservices and APIs using Python and FastAPI. Develop scalable and secure backend systems supporting AI workloads. Implement authentication, authorization, and enterprise security standards. Optimize inference performance and operational efficiency. Evaluation, Monitoring & Governance Implement monitoring and observability mechanisms for conversational AI applications. Track retrieval performance, response quality, latency, user feedback, and model usage. Develop evaluation frameworks for grounding, correctness, relevance, and user satisfaction. Follow Responsible AI, security, privacy, and governance standards.

Required Skills: Conversational AI Enterprise Chatbots Virtual Assistants AI Copilots Multi-turn Conversations Conversational Design Context Management RAG & Knowledge Systems Retrieval-Augmented Generation (RAG) Semantic Search Embedding Models Hybrid Search Knowledge Retrieval Vector Search Optimization AI / LLM Frameworks LangChain LangGraph LlamaIndex Semantic Kernel CrewAI (Preferred) Programming Python FastAPI REST APIs SQL Git Vector Databases & Search Pinecone Qdrant Weaviate PGVector FAISS Azure AI Search / Elasticsearch Cloud Platforms Azure OpenAI / Azure AI Foundry AWS Bedrock Google Vertex AI Experience building enterprise knowledge assistants. Experience integrating SharePoint, Microsoft 365, Confluence, ServiceNow, Salesforce, or other enterprise knowledge sources. Knowledge of Agentic AI and multi-agent architectures. Experience with LLMOps, evaluation frameworks, and AI observability tools. Cloud certifications (Azure/AWS/GCP). Experience deploying containerized AI applications using Docker and Kubernetes.