- Design and develop scalable backend services and AI integrations using .NET (C#, ASP.NET Core)
- Implement tool-calling, memory management, and structured context handling for LLM-driven systems
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines using embeddings and vector databases
- Develop and orchestrate agentic workflows using frameworks such as Semantic Kernel, LangChain, LlamaIndex, or AutoGen
- Apply advanced prompt engineering techniques including ReAct, Chain-of-Thought (CoT), function-calling, and structured outputs
- Integrate Azure OpenAI, Gemini, and other LLM APIs into enterprise-grade applications
- Develop and manage secure APIs using REST, WebSockets, and implement authentication using OAuth2 and JWT
- Implement caching, logging, monitoring, and performance optimization for AI-powered services
- Build and deploy cloud-native applications using Microsoft Azure services (App Services, Functions, API Management, Service Bus)




- Containerize and deploy applications using Docker and orchestrate using Azure Kubernetes Service (AKS) where required
- Develop high-performance and scalable solutions using asynchronous programming, parallel processing, and streaming in .NET
- Work extensively with embeddings, vector databases, and Azure Cognitive Search for semantic retrieval
- Apply best practices in prompt engineering to improve LLM accuracy, relevance, and reliability
- Ensure secure and effective communication using web protocols such as HTTP, REST, and WebSockets
- Implement CI/CD pipelines and DevOps practices using Azure DevOps
- Monitor and troubleshoot applications using Azure Monitor, Application Insights, and logging frameworks
- Ensure compliance with security, governance, and data privacy standards in AI implementations

📌 Lead Software Engineer (Hyderabad)
🏢 Virtusa
📍 Hyderabad