Agentic Operations Architect

Role overview A company that builds payroll, benefits, and HR software for small businesses is hiring an Agentic Operations Architect to own the patterns, primitives, standards, and shared tooling that let other builders across the organization ship agentic service workflows faster and more safely. The role is not the owner of any single workflow; instead it sets the bar so that the tenth workflow ships faster and with more safeguards than the first, while prototyping selectively to validate patterns and prove out gaps in the underlying platform.

Responsibilities - Design reusable patterns for agentic service workflows, including orchestration, human-in-the-loop protocols, override and escalation logic, and quality safeguards, so other builders assemble from proven components. - Set concrete standards builders work to, prototype workflows selectively to validate a pattern or unblock a hard problem, then extract the reusable part and hand it off. - Influence Product on what to build next by turning what slows builders down into specific, prioritized asks backed by evidence, and prototype around platform gaps to prove capability worth investing in. - Rank automation opportunities by volume, risk, and customer impact using SOPs, operational metrics, and interaction data, and work with Data to define how workflow performance is measured. - Surface customer stakes to Legal, Security, Compliance, and platform reviews so requirements land in the patterns instead of getting retrofitted per workflow, and represent how the portfolio is performing to senior stakeholders.

Requirements - 8+ years in operations, product, or AI roles, with at least 2 years designing and deploying AI-assisted or agentic workflows in production. - Hands-on experience with agentic tooling, orchestration frameworks, or MCP-style integrations, including multi-agent coordination, beyond conceptual familiarity. - Strong fluency with LLM systems, including prompt design, evaluation, and how models actually behave at scale. - Experience designing human-in-the-loop systems with clear escalation logic, override controls, and compliance-aware checkpoints. - Ability to define and diagnose workflow metrics such as solve and assist rate, containment, and escalation quality, and to tell a real regression from noise. - Proven track record influencing Product, Engineering, Legal, Security, and Compliance in writing, in design reviews, and in high-stakes forums, with familiarity in Responsible AI practices, governance, and risk management in production, and prior experience building the plane while flying it.

Nice to have - Experience with RAG architectures and retrieval quality optimization, plus the ability to assess whether underlying data structures, quality, and governance can support reliable agentic performance. - Background in SaaS, fintech, or other regulated environments where compliance constraints are real, and exposure to AI governance or safety-oriented review processes.

Benefits and work setup - Cash compensation of $168,420 to $210,525 USD per year in Denver and most major metros, and $197,895 to $247,369 USD per year in San Francisco and New York, with final offers determined by multiple factors. - Hybrid work expectation of approximately 2 to 3 days per week in physical offices in Denver, San Francisco, or New York City, with secure internet required for any remote days.