AI Solutions Architect

Responsibilities

• Architect, prototype, and own end-to-end agentic service workflow frameworks, from scoping through production deployment and iteration — including solve and assist targets, HITL protocols, override logic, and downstream quality safeguards.
• Analyze SOPs, operational metrics and interaction data to identify and prioritize high-impact automation opportunities based on volume, risk, and customer impact.
• Design and implement multi-agent orchestration patterns across tools, data sources, and decision steps within a single end-to-end workflow.
• Apply and influence AI platform capabilities in partnership with CoreX (Gusto's AI Platform team) — including orchestration, retrieval, and evaluation — helping define what needs to be built to support production workflows at scale.
• Identify platform gaps, prototype workflow-level solutions, and partner with engineering to shape the primitives required for reliable, scalable AI systems.
• Serve as the primary CX voice in Legal, Security, Compliance, and CoreX forums — translating CX quality stakes and workflow risk into terms each audience acts on, and ensuring governance requirements are embedded in design, not retrofitted after launch.
• Strengthen evaluation frameworks and feedback loops to ensure quality, compliance, and continuous improvement; contribute to Gusto's human evaluation programs and AI governance practices through deep partnership with our internal CX Labs team.
• Partner with Data teams to define and track workflow performance — including solve and assist rate, AHT, rework rate, and customer effort score — clearly distinguishing between model-level, workflow-level, and operational drivers.
• Build ROI models to quantify workflow impact across efficiency, quality, and cost before and after deployment.
• Represent workflow performance and risk to senior stakeholders with appropriate precision and brevity; communicate in a way that drives action, not overwhelm.
• Lead through ambiguity and rapid change: the function is still being defined, and you will help define it.

Requirements

• 8+ years in operations, product, or AI roles — with at least 2 years designing and deploying AI-assisted or agentic workflows.
• Strong fluency with LLM systems, including prompt design, evaluation, and production behavior at scale.
• Hands-on experience with agentic tooling, orchestration frameworks, or MCP-style integrations.
• Experience designing human-in-the-loop (HITL) systems with clear escalation logic, override controls, and compliance-aware checkpoints.
• Working knowledge of multi-agent systems and tool coordination.
• Strong operational judgment: able to define and diagnose workflow metrics.
• Proven track record influencing cross-functional stakeholders — including Product, Engineering, Legal, Security, and Compliance — in writing, in design reviews, and in high-stakes forums.
• Familiarity with Responsible AI practices, governance, and risk management in production environments.
• Proven ability to operate in high ambiguity, create clarity, and drive alignment across technical and non-technical audiences.
• Strong systems thinking with a bias toward execution and measurable outcomes.
• Deep empathy for small business customers and the employees who serve them.

Compensation

• Cash compensation: $133,470/yr to $173,511/yr in Denver & most major metro locations, and $157,145/yr to $204,289/yr for San Francisco & New York.
• All full-time employees receive competitive base pay, benefits, and equity (RSUs).