aita consulting servicesAtlanta, GA
Agentic AI / Semantic Solutions Architect
Hybrid Position Experience Requried: 13+YearsRole Overview We are seeking a highly skilled Agentic AI / Semantic Solutions Architectto design and prototype advanced agent-layer architectures that operate on enterprise semantic data platforms. This role sits at the intersection ofLLM orchestration, knowledge graphs, and semantic data modeling, focusing on buildingPOC-level intelligent agent solutionsrather than production-scale systems. The ideal candidate will have deep expertise inagent-based AI systems, GraphRAG architectures, and context engineering, with the ability to design frameworks where autonomous agents can effectively interpret and reason over structured knowledge.
Key Responsibilities:
Architect and designagentic AI workflowsthat consume outputs from semantic layers, includingknowledge graphs, ontologies, and metadata catalogs
Develop and prototype GraphRAG pipelinesthat combine graph traversal with vector-based retrieval for accurate, domain-grounded responses
Define and implementcontext 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
DevelopLLM orchestration workflowsusing frameworks such asLangChain, LangGraph, LlamaIndex, or AutoGen
Build pipelines forautomated metadata extraction and semantic taggingusing NLP and LLM-based approaches
Collaborate with Semantic Data Architectsto 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 Mandatory SkillsStrong expertise inAgentic AI architecture(multi-agent systems, tool usage, planning loops)
Hands-on experience with GraphRAG design(hybrid graph + vector retrieval systems)
Experience inLLM orchestration frameworks :LangChain, LangGraph, LlamaIndex, or AutoGenDeep understanding ofcontext 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
Nice to Have:
Skills Experience with Google Vertex AI (Agent Builder / Search)
Knowledge ofGCP Spanner Graph
Familiarity with metadata platforms like Collibra or Google Dataplex
Experience withvector databases :Pinecone, Weaviate, pgvector, Vertex AI Vector SearchPrior experience inregulated domainssuch as financial services or legal systems
Also on the board Same function, level within a rung
Level
Lead
Location
Atlanta, GA
Occupation
Computer Systems Engineers/Architects
Industry
Computer Systems Design Services
Posted
yesterday