Principal Engineer

Role: Principal Gen AI Engineer

Location: India (Remote/Hybrid)

Experience: 8–13 Years

Notice Period: Immediate (Serving Notice Period)

We are hiring Principal GenAI Engineer to lead the design and delivery of enterprise-scale AI solutions for Fortune 500 clients. This is an opportunity to work on cutting-edge Graph-powered Retrieval-Augmented Generation (Graph-RAG) systems that combine Knowledge Graphs with advanced Large Language Models (LLMs) to build scalable, explainable, and production-ready AI applications.

Key Responsibilities

• Design and develop enterprise-grade Graph-RAG solutions using LLMs and Knowledge Graphs.
• Build scalable Retrieval-Augmented Generation (RAG) pipelines and AI agent workflows.
• Develop production-ready applications using Python, LangChain, and LangGraph.
• Design and optimize Knowledge Graph architectures for semantic reasoning.
• Create and maintain ontologies, taxonomies, and semantic data models.
• Implement entity resolution, relationship extraction, and graph enrichment pipelines.
• Integrate Knowledge Graphs with vector databases to enable hybrid retrieval.
• Deploy and optimize GenAI applications on AWS, Azure, or GCP.
• Collaborate with cross-functional teams to deliver enterprise AI solutions with high performance, explainability, and reliability.

Required Skills

• 8–13 years of experience in Machine Learning, Artificial Intelligence, or related domains.
• 2+ years of hands-on experience with Large Language Models (LLMs).
• Expertise in Knowledge Graphs and Graph-RAG.
• Hands-on experience with Neo4j, Amazon Neptune, or similar graph databases.
• Strong understanding of explainable AI and techniques to reduce LLM hallucinations.
• Retrieval-Augmented Generation (RAG)
• Strong knowledge of Cypher or other graph query languages.
• AI Agents
• Prompt Engineering
• Python
• LangChain
• LangGraph
• SQL
• Experience deploying GenAI solutions on AWS, Azure, or Google Cloud Platform (GCP).