We are looking for an Agentic AI Architect I to help design scalable, reliable, and reusable architectures for production-grade AI agents. This role supports the AI Center of Excellence mission by helping product and engineering teams build, integrate, release, evaluate, and operate agentic AI solutions using shared platform capabilities and consistent architectural patterns. 

You will work across product, engineering, AI Platform, infrastructure, QA/Eval, operations, and support teams to translate business and workflow requirements into practical agent architectures. Your work may span agent orchestration, runtime services, tool and system integrations, workflow execution, observability, evaluation, responsible AI controls, and production support. 

This is a hands-on architecture role for someone who can balance technical design, implementation practicality, reliability, and delivery speed. The successful candidate will help teams avoid fragile one-off solutions by identifying reusable patterns that can be adopted across AI agent products. 

Primary Responsibilities 

• Design end-to-end architectures for agentic AI solutions, including orchestration, runtime execution, workflow management, tool invocation, system integrations, evaluation, observability, and supportability. 

• Translate product requirements, business workflows, and customer use cases into clear technical designs and implementation plans. 

• Define reusable patterns for multi-step agent behavior, task routing, handoffs, cross-system interactions, state management, and multi-agent coordination where appropriate. 

• Partner with AI Platform teams to use shared orchestration, runtime, evaluation, reporting, monitoring, and developer-tooling capabilities. 

• Collaborate with engineering teams during implementation through architecture reviews, design guidance, technical documentation, and production-readiness assessments. 

• Evaluate architecture tradeoffs involving scalability, reliability, performance, security, maintainability, cost, developer experience, and delivery speed. 

• Help define integration patterns for APIs, enterprise systems, data sources, tools, model services, and Model Context Protocol, or MCP, capabilities. 

• Establish observability requirements, including logging, metrics, traces, dashboards, alerts, debugging workflows, and operational reporting. 

• Partner with QA/Eval teams to incorporate evaluation criteria, regression coverage, testing strategies, and quality controls into agent architecture. 

• Support release planning, launch-readiness reviews, production monitoring, incident response, and post-release improvement. 

• Identify repeated solution patterns and recommend when they should become shared product or platform capabilities. 

• Contribute to architecture standards, reference designs, technical decision records, implementation guidance, and reusable documentation. 

• Help teams apply responsible AI, privacy, security, governance, and human oversight requirements throughout the solution lifecycle. 

• Communicate technical decisions, dependencies, risks, and recommendations clearly to engineering, product, operations, and business stakeholders. 

Required Knowledge, Skills, and Abilities 

• Experience designing or building backend systems, distributed applications, workflow platforms, integration services, developer platforms, cloud applications, or AI-enabled solutions. 

• Working knowledge of APIs, asynchronous processing, service coordination, event-driven architectures, stateful systems, and enterprise integrations. 

• Understanding of architecture principles related to scalability, reliability, performance, availability, maintainability, security, and production support. 

• Familiarity with LLM-based applications, AI agents, retrieval techniques, prompt and context management, tool calling, workflow automation, or model-driven products. 

• Ability to convert business and workflow requirements into practical technical architectures. 

• Experience with cloud services, deployment pipelines, monitoring, logging, dashboards, and production troubleshooting. 

• Understanding of testing, evaluation, regression coverage, release readiness, and operational support for production systems. 

• Ability to evaluate technical alternatives and explain architecture tradeoffs to technical and nontechnical stakeholders. 

• Strong written and verbal communication skills, including the ability to produce clear diagrams, design documents, decision records, and implementation guidance. 

• Strong collaboration skills across engineering, product, QA/Eval, security, infrastructure, operations, and support teams. 

• Ability to work effectively in an evolving technical environment where requirements and agentic AI patterns may continue to mature. 

Preferred Qualifications 

• Experience designing or implementing production LLM applications, AI agents, workflow automation, or intelligent assistant solutions. 

• Familiarity with agent orchestration frameworks, model gateways, evaluation frameworks, vector search, retrieval-augmented generation, and AI observability. 

• Experience integrating AI solutions with enterprise platforms, internal services, APIs, data sources, and third-party tools. 

• Familiarity with Model Context Protocol, tool integration primitives, structured outputs, agent memory, workflow state, and multi-agent patterns. 

• Experience with responsible AI practices, including safety controls, access management, data protection, human oversight, and auditability. 

• Experience creating reusable reference architectures, platform patterns, technical standards, or architecture governance. 

• Familiarity with production incident management, reliability engineering, deployment strategies, and post-release support. 

• Relevant cloud, software architecture, data, security, or AI certifications are beneficial but not required. 

• Health, dental, and vision insurance.
• Retirement savings plan with company match.
• Paid time off and holidays.
• Professional development opportunities.
• Performance-based bonus based on position.

#LI-JK1 #LI-REMOTE