Overview
Design and build enterprise-grade, production-ready conversational and Agentic AI systems that enhance how users interact with enterprise products, services, insights, and recommendations.
What you'll do
- Design, develop, and deploy production-grade GenAI solutions using advanced LLMs (OpenAI APIs such as GPT-4.1, GPT-4o, etc.).
- Implement Retrieval-Augmented Generation (RAG) pipelines using structured and unstructured enterprise data.
- Design hybrid search architectures combining Vector DBs and Graph DBs (e.g., Azure AI Search, Neo4j) for semantic, contextual, and relationship-based retrieval.
- Build Agentic AI workflows using frameworks such as LangChain, LangGraph, and Haystack, including multi-agent orchestration (planner, retriever, evaluator, executor agents), tool-calling, function execution, system-to-system automation, and memory management (short-term, long-term, and session-based).
- Develop and integrate AI-powered chatbots and agents within the Azure ecosystem, ensuring interoperability with existing platforms and services.
- Integrate GenAI solutions with enterprise systems using APIs, event-driven architectures, and message brokers.
- Build secure, scalable backend leveraging Azure App Services, Azure Functions, Bot Framework, Azure Cache for Redis, and related services.
- Work closely with Cloud, Digital, Data Engineering, and Business teams to drive adoption and real-world impact.
- Implement guardrails for safety, hallucination control, data privacy, and responsible AI.
- Ensure enterprise-grade governance, including access control, auditability, and compliance with internal policies.
- Apply MLOps / LLMOps best practices: model/version management, prompt versioning, CI/CD pipelines for GenAI applications, automated prompt, retrieval, and regression testing, and monitoring, logging, and observability for LLM outputs.
- Analyze chatbot and agent performance using quantitative and qualitative metrics (accuracy, latency, adoption, task completion).
- Optimize prompts, retrieval strategies, agent flows, and system performance based on real usage data.
- Drive continuous enhancement of user experience through experimentation and feedback loops.
What you'll need
- Strong understanding of LLMs, transformers, embedding, prompt engineering, and evaluation techniques.
- Experience building end-to-end GenAI/Agentic AI products, including backend services and frontend web apps.
- Hands-on experience with LangChain, LangGraph, n8n, Co-pilot for building modular, agent-based systems.
- Practical experience designing multi-agent architectures and orchestrating reasoning and action workflows.
- Strong experience with Vector Databases and Graph Databases (Azure AI Search, Neo4j, Databricks Vector DB) for hybrid, semantic and relationship-driven search.
- Proven experience implementing RAG pipelines with structured and unstructured enterprise data.
- Proficiency in Python, SQL, Spark, and familiarity with additional languages (e.g., JavaScript).
- Hands-on experience with PyTorch and TensorFlow.
- Experience working with high-performance, large-scale ML systems in production environments.
- Ability to solve complex problems in language understanding, reasoning, and GenAI system design.
- Experience deploying GenAI solutions on Azure, including Azure Data Factory (ADF), Databricks, Azure AI Search, Databricks Genie, AI Document Intelligence, App Services, Azure Functions, Bot Framework, and Azure Cache for Redis.
Details
- Locations: Hyderabad, Noida, Chennai, Uttar Pradesh, India.
Read the full description and apply on the company’s own careers page.