Job Title: AI Architect

Location: Blue Ash, OH, 45242, US

Job Duration: 6 Month Contract To Hire

PR: $80/hr - $100/hr on W2 only

Must Haves:

• Python
• LangChain/LangGraph
• MCP Servers
• RAG/Vector DBs
• GCP, AZURE, Kubernets /Ci/CD
• LLM Integrations + Agentic SDLC

SUMMARY

• The AI Enablement team at Client is seeking an AI Architect – Agentic Platforms to define the architectural foundations that power Client enterprise agent ecosystem. This role is responsible for designing and governing the architecture for agent-based integrations, agent registries, scoring/evals infrastructure, grounding patterns, and multi-agent orchestration platforms.
• The AI Architect provides deep technical leadership across engineering, product, data science, security, and cloud teams to ensure that agents are built safely, consistently, and with enterprise-grade reliability, performance, and observability. This role combines expertise in large-scale AI systems, distributed cloud architecture, and modern agentic frameworks.

AI Agentic Platform Technical Leadership

• Define and evolve the enterprise reference architecture for AI agents, including orchestration frameworks, tool integration patterns, MCP servers, registries, and multi-agent coordination
• Design large-scale agent orchestration platforms that enable autonomous workflows across commerce, operations, and internal productivity domains
• Responsible for operational uptime adhering to SLAs, planning upgrades, rolling out new capabilities and integrations for agent platform.
• Establish grounding patterns using semantic layers, vector search, knowledge models, and Retrieval-Augmented Generation (RAG)
• Architect and develop systems that connect agents to trusted enterprise data, APIs, and business services
• Develop architectural patterns for safe, governed agent execution aligned with Responsible AI principles

Enterprise Platform Engineering Excellence

• Architect scalable, fault-tolerant AI agent platforms across hybrid cloud environments (Azure & GCP)
• Establish architecture standards ensuring low latency, high availability, resiliency, and observability.
• Partner with cloud and platform engineering teams to deliver containerized, API-driven, secure infrastructure for agent workloads
• Define platform lifecycle patterns including versioning, release gating, rollback strategies, and performance benchmarking
• Enable cost-efficient scaling of AI workloads across millions of enterprise and customer interactions

Agent Quality, Safety & Evaluation Innovation

• Define, develop and operationalize the Agentic SDLC, including evaluation frameworks, safety testing, regression gates, and release readiness criteria
• Architect systems for continuous agent improvement using automated evaluation pipelines and human feedback loops
• Establish enterprise standards for hallucination mitigation, prompt safety, PII protection, and AI misuse prevention
• Lead observability and AIOps patterns for agent monitoring, anomaly detection, and operational intelligence
• Define performance scoring frameworks for agent quality, reliability, and cost optimization

Strategic AI Platform Innovation

• Partner with engineering, product, and data science leaders to deliver intelligent agent platforms serving customer and enterprise use cases
• Drive innovation in multi-agent systems, LLM-powered workflows, and AI orchestration technologies
• Evaluate emerging agent frameworks, tooling, and open standards to guide platform strategy and build-vs-buy decisions
• Contribute to platform engineering excellence by building reusable AI infrastructure and developer enablement capabilities
• Provide architectural mentorship and technical guidance across teams on agentic AI design, scalable engineering practices, and enterprise AI standards