Agentic AI Architect

Overview In this role you design and build agentic AI systems across industries, blending GenAI, ML, and systems engineering for production-ready agents. You will shape governance, observability, and safety in enterprise environments while advancing knowledge graphs and advanced retrieval. You work with cross-functional teams to deploy scalable AI architectures and deliver measurable performance. This is a chance to influence enterprise AI at scale within a global tech leader. Compensation / Benefitsmedical, dental, and vision insurance401k program with company matchpaid time offflexible spending or health savings accountlife and AD&D insurancedisability coverage ResponsibilitiesDesign and implement multi-agent AI systems coordinating specialized agents, tools, and workflowsDevelop agent orchestration frameworks covering planning, reasoning, memory management, and autonomous decision-makingDefine enterprise patterns for governance, observability, evaluation, and safety controlsEstablish standards and best practices for Agentic AI, GenAI, Knowledge Graphs, and retrieval systemsDesign and implement Knowledge Graph and Graph RAG architectures to improve reasoning and retrievalBuild and maintain enterprise knowledge models using ontologies, semantic relationships, and graph databasesDevelop retrieval pipelines combining vector search, hybrid search, graph traversal, and semantic techniquesSet up evaluation pipelines for agent performance, reasoning quality, and retrieval effectiveness with methods for hallucination detection and groundingProduce production-grade AI systems with scalable deployment Key requirements8+ years in Python-based AI systemsProven track record deploying agentic AI systems in production3+ years architecting enterprise-scale agentic AI solutions using frameworks like CrewAI, LangChain, LangGraph, AutoGen, StrandsExperience designing multi-agent architectures, tool-calling, planning/reasoning, and orchestration patternsKnowledge Graphs and retrieval architectures with Neo4j, AWS Neptune, RDF, SPARQL, vector databases, graph-based RAGStrong understanding of Graph RAG, embeddings, vector search, and semantic retrievalBachelor in Computer Science or equivalent work experienceability to explain AI decisions to non-technical stakeholdersstrong learning mindset and adaptabilitycomfortable collaborating with subject-matter expertsPythonCrewAILangChain