AI Architect

AI Architect at Ascendum Solutions AI Architect at Ascendum Solutions in Fort Thomas, Kentucky Posted in 1 day ago.

Type:

full-time

Job Description:

Seeking an AI Architect - Agentic Platforms to define the architectural foundations that power company's 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. About the Role experience in cloud and distributed systems architecture focused on scalability, reliability, observability, and performance. designing enterprise AI/ML systems; 1+ years hands-on with GenAI, agentic workflows, RAG, LLM-based integrations, or multi-agent systems. Strong expertise with agentic frameworks and tooling (MCP, LangChain, LangGraph,LlamaIndex, autogen, crewai, Agent sdk,OpenAI SDK etc). Hands-on experience in modern software development and engineering practices. Proven experience integrating APIs and enterprise systems into agentic platforms and workflows. Ability to rapidly build AI-driven prototypes, proofs of concept, and demo-ready product experiences. Experience defining and governing enterprise architecture standards, patterns, and reference architectures. Deep understanding of MCP servers, tool calling, registries, eval pipelines, agent observability, and multi-agent orchestration. Hands-on experience with Azure and GCP, including Kubernetes, containerization, identity, networking, CI/CD, and API platforms. Familiarity with AIOps/MLOps stacks (MLflow, model registries, vector DBs, semantic layers, feature stores, monitoring). Strong knowledge of security, compliance, risk, and Responsible AI (RAI) considerations for enterprise agent systems. Demonstrated ability to partner across engineering, data science, product, and security teams to deliver complex AI platform architectures. Responsibilities 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