About the Role

We are seeking a Senior AI Engineer to design and build Graph-powered Retrieval-Augmented Generation (Graph-RAG) systems that combine structured semantic reasoning with advanced Large Language Model (LLM) architectures. You will work on production-grade AI systems that integrate knowledge graphs, vector search, and LLM pipelines to deliver scalable, explainable, and enterprise-ready AI applications. This role is ideal for engineers passionate about next-generation AI architectures, knowledge graphs, and intelligent retrieval systems.

• Design and build Graph-RAG architectures combining knowledge graphs with LLM pipelines
• Develop semantic retrieval systems using vector databases and graph databases
• Build scalable LLM-based reasoning systems with explainable outputs
• Integrate structured data, graph relationships, and unstructured documents into unified AI pipelines
• Implement AI agents and orchestration frameworks for complex query reasoning
• Develop APIs and services for enterprise AI applications
• Optimize AI pipelines for performance, latency, and scalability

• Strong programming experience in Python
• Experience building LLM applications and RAG pipelines
• Knowledge of Graph-RAG architectures and knowledge graphs
• Experience with vector databases (Pinecone, Weaviate, FAISS, Chroma)
• Experience with graph databases (Neo4j, TigerGraph, Amazon Neptune)
• Familiarity with LLM frameworks such as LangChain, LlamaIndex, or LangGraph
• Strong understanding of semantic search and embeddings

• Experience with advanced LLM architectures (GPT, Claude, Llama, Mistral)
• Knowledge of agentic AI workflows and reasoning systems
• Experience deploying AI systems on cloud platforms (AWS, Azure, GCP)
• Experience building production-grade AI pipelines and microservices
• Background in knowledge representation and semantic reasoning

• Full Name

• Email

• Phone

• Current Location

• Work Authorization

• Total Years of Experience

• LinkedIn Profile

• Availability to Start

• Expected Salary