Key Responsibilities

• 
  
• Design and build production-grade AI agents with planning, reasoning, and tool-use capabilities.
• 
  
• Architect stateful agent workflows using orchestration frameworks such as LangGraph or AutoGen.
• 
  
• Build and productionize Retrieval-Augmented Generation (RAG) pipelines, including data ingestion, embedding strategies, retrieval optimization, and re-ranking.
• 
  
• Integrate Large Language Models (LLMs) with enterprise systems through APIs, tools, and external data sources.
• 
  
• Optimize retrieval performance, ranking strategies, and overall RAG architecture.
• 
  
• Establish evaluation frameworks, observability, guardrails, and monitoring for LLM applications, focusing on accuracy, safety, latency, and cost.
• 
  
• Deploy, maintain, and scale AI applications using Docker, Kubernetes, and Azure cloud services.
• 
  
• Contribute to technical architecture, mentor fellow engineers, and help define engineering best practices for agentic AI development.