Description

Key Responsibilities:

• Architect and design agentic AI workflows that consume outputs from semantic layers, including knowledge graphs, ontologies, and metadata catalogs
• Develop and prototype GraphRAG pipelines that combine graph traversal with vector-based retrieval for accurate, domain-grounded responses
• Define and implement context engineering strategies, including metadata injection, chunking, and semantic optimization for LLM prompts
• Design and build Model Context Protocol (MCP) server patterns to enable seamless interaction between agents and semantic data systems
• Develop LLM orchestration workflows using frameworks such as LangChain, LangGraph, LlamaIndex, or AutoGen
• Build pipelines for automated metadata extraction and semantic tagging using NLP and LLM-based approaches
• Collaborate with Semantic Data Architects to ensure ontologies and graph structures are optimized for agent traversal and querying
• Prototype agent-based solutions for business use cases such as:
• Credit risk analysis
• Customer data onboarding workflows

Key Requirements and Technology Experience: 

• Key skills; "Agentic" ,"RAG"," LLM", "Lang Chain"
• Strong expertise in Agentic AI architecture (multi-agent systems, tool usage, planning loops)
• Hands-on experience with GraphRAG design (hybrid graph + vector retrieval systems)
• Experience in LLM orchestration frameworks:
• LangChain, LangGraph, LlamaIndex, or AutoGen
• Deep understanding of context engineering techniques (chunking, windowing, semantic compression)
• Experience designing and integrating Model Context Protocol (MCP)
• Strong knowledge of semantic systems such as:
• Knowledge graphs
• Ontologies
• Metadata-driven architectures

Key Skills

Education

Any Graduate