Agentic AI Architect

NTT DATA Services•Dallas, TX

54d•$122,648 - $283,906•Remote

About The Position

NTT DATA is seeking an Agentic AI Architect to join their team. This role involves designing and building agentic AI systems across multiple industries by combining GenAI, ML, and systems engineering to create production-ready AI agents that interact with machines, data streams, and enterprise systems.

Requirements

8+ Years of Strong experience in Python-based AI systems
Demonstrated experience building and deploying agentic AI systems in production environments.
3+ years architecting and deploying enterprise-scale agentic AI solutions using frameworks such as CrewAI, LangChain, LangGraph, AutoGen, Strands, or equivalent orchestration platforms
Experience designing and implementing multi-agent architectures, agent workflows, tool-calling systems, planning/reasoning agents, and agent orchestration patterns
Experience with Knowledge Graphs, semantic data models, and retrieval architecture, including technologies such as Neo4j, AWS Neptune, RDF, SPARQL, vector databases, graph-based RAG, or similar enterprise knowledge systems
Strong understanding of advanced retrieval techniques including Graph RAG, hybrid search, knowledge-grounded AI systems, embeddings, vector search, and semantic retrieval strategies
Bachelor’s in computer science or equivalent work experience

Nice To Haves

Experience building production grade AI systems (not just prototypes)
Ability to explain AI decisions to non-technical stakeholders
Multiple Industry Domains experience
AWS, GCP, or NVIDIA AI stack experience
Knowledge of model governance and explainability
Experience with document intelligence pipelines
Comfortable working with subject-matter experts
Strong learning mindset and adaptability

Responsibilities

Design and implement multi-agent AI systems that coordinate specialized agents, tools, and enterprise workflows.
Develop agent orchestration frameworks, including planning, reasoning, memory management, task decomposition, and autonomous decision-making capabilities.
Define architectural patterns for agent governance, observability, evaluation, and safety controls in enterprise environments.
Define enterprise architecture standards, reference implementations, and best practices for Agentic AI, GenAI, Knowledge Graphs, and retrieval systems.
Design and implement Knowledge Graph and Graph RAG architectures to improve reasoning, contextual understanding, and retrieval accuracy.
Build and maintain enterprise knowledge models using ontologies, semantic relationships, metadata, and graph databases.
Develop advanced retrieval pipelines combining vector search, hybrid search, graph traversal, and semantic retrieval techniques.
Establish frameworks for measuring agent performance, reasoning quality, task completion accuracy, and retrieval effectiveness.
Build evaluation pipelines for agentic systems, including hallucination detection, grounding validation, and response quality metrics.