Staff/ Principa/ MTS Agentic AI Architect – Knowledge Engineering

Our vision is to transform how the world uses information to enrich life for all . Micron Technology is a world leader in innovating memory and storage solutions that accelerate the transformation of information into intelligence, inspiring the world to learn, communicate and advance faster than ever.

Responsibilities

• AI Strategy & Architecture: Define and drive enterprise architecture for Agentic AI, Knowledge Engineering, and AI-powered decision systems across AWS, GCP, and on-prem environments.
• Agentic AI Platforms: Design scalable multi-agent architectures using A2A collaboration, memory systems, reasoning frameworks, tool use, and workflow orchestration.
• Claude & AWS AgentCore Enablement: Architect agentic workflows that leverage the Claude ecosystem, Claude Code-style engineering workflows, and AWS AgentCore-based agent runtime patterns.
• MCP-Based Connectivity: Architect MCP-based access patterns that allow agents to securely interact with enterprise tools, APIs, knowledge repositories, data platforms, and engineering systems.
• Knowledge Engineering: Architect enterprise knowledge fabrics, ontologies, taxonomies, metadata models, and knowledge graphs for engineering and manufacturing use cases.
• RAG & GraphRAG Solutions: Design and optimize retrieval, semantic search, grounding, citation, graph traversal, and context engineering frameworks.
• Knowledge Management: Develop LLM Wiki architecture, knowledge curation workflows, governance, and knowledge lifecycle processes.
• Semantic Integration: Implement entity resolution, schema mapping, semantic interoperability, and cross-source knowledge integration across cloud and on-prem sources.
• AI-Powered Reasoning: Build graph traversal, semantic reasoning, and context-aware agent capabilities across connected knowledge ecosystems.
• Hybrid Platform Architecture: Design technology-agnostic AI solutions across AWS, GCP, on-premises compute, Kubernetes, distributed storage, and hybrid data platforms.
• AI Governance: Establish standards for security, compliance, access control, observability, explainability, Responsible AI, and operational excellence.
• Technology Leadership: Evaluate emerging technologies, define reference architectures, and drive AI platform adoption across engineering organizations.
• multi-functional Collaboration: Partner with engineering, manufacturing, product, validation, data, and business teams to identify and deliver high-value AI solutions.
• Innovation & Enablement: Lead proof-of-concepts, mentor technical teams, and promote standard processes in Agentic AI, Knowledge Engineering, and software architecture.

Expertise Applying Artificial Intelligence in workflows to improve build efficiency

• Claude Ecosystem: Claude, Claude Code-style coding workflows, prompt/context design, agentic engineering workflows, skill-based automation, MCP-enabled tool access, and enterprise adoption patterns.
• AWS AgentCore & AWS AI Architecture: AWS AgentCore, AWS-native and hybrid agent runtime patterns, compute, storage, serverless, large-scale data processing, managed graph or retrieval services, and secure enterprise deployment patterns.
• Agentic AI & A2A Systems: A2A-based agent collaboration, ReAct, Plan-and-Execute, Reflection, Supervisor Patterns, Tool Use, Memory Systems, and Workflow Orchestration.
• MCP & Tool Connectivity: MCP-based integration with enterprise tools, APIs, data sources, knowledge repositories, agent tools, and governed execution environments.
• Generative AI & Retrieval: Large Language Models, RAG, GraphRAG, Semantic Search, Retrieval Optimization, Reranking, Grounding, and Context Engineering.
• Knowledge Graphs & Semantic Systems: Ontology Engineering, Taxonomy Design, Semantic Modeling, Knowledge Representation, and Enterprise Knowledge Architecture.
• Graph Technologies: Neo4j, AWS Neptune, RDF/OWL, Property Graphs, Graph Traversal, Graph Reasoning, Cypher, and SPARQL.
• Vector Databases: Pinecone, ChromaDB, Weaviate, Milvus, Qdrant, FAISS, and similar retrieval platforms.
• AI Development Frameworks: Python, LangChain, LlamaIndex, LangGraph, Claude Code-compatible workflows, and AI Orchestration Frameworks.
• Document Intelligence & Knowledge Ingestion: JIRA, Confluence, SharePoint, Bitbucket, Wikis, Specifications, Technical Documents, and Enterprise Knowledge Repositories.
• Embedding & Retrieval Pipelines: Embedding Models, Metadata Extraction, Vectorization, Indexing, Document Pro…