AI Domain Architect

Distro•Denver, CO

2d•Hybrid

About The Position

Teach AI what our business actually means. PEO and HCM are dense domains. Co-employment, payroll, benefits, workers' compensation, and multi-state compliance carry meaning that a general-purpose model simply does not have. Those domains anchor a family of PrismHR platforms, and your job is to encode that meaning so every AI capability we publish reasons about our domain correctly. You will join the AI Domain team, which owns the enterprise standards, reference architectures, approved model catalog, and governance safeguards for AI across the company. Within it you own the domain intelligence layer: the ontology, the agent workflow models, the fine-tuning strategy, and the intelligence pattern library that product teams build on. This is a hands-on senior individual contributor role patterns here are proven through working proof-of-concepts before they become standards, so you will build as much as you write. Four areas of ownership. The canonical ontology as a semantic layer spanning all PrismHR platforms entities, relationships, business rules, and terminology across co-employment, payroll, benefits administration, workers' compensation, onboarding, and compliance built with the product teams who own each data model, and governed as a living artifact. Agent workflow modeling: business processes decomposed into agentic workflows with tool boundaries, decision points, escalation paths, and human-in-the-loop checkpoints, defining where agents may act autonomously and where they must defer, especially around payroll, money movement, and compliance. Fine-tuning strategy: when to fine-tune, when to retrieve, when prompting is enough, with dataset curation standards covering labeling, provenance, retention, and residency, and domain-specific evaluation harnesses that measure accuracy in PEO and HCM rather than on generic benchmarks. And the intelligence pattern library: retrieval strategies, reasoning templates, agent scaffolds, and validation guards, each proven by a working proof-of-concept before publication and documented with its failure modes. You will engage with product teams from design through go-live, advise on use-case feasibility and risk, act as the escalation point for domain-AI design questions, and contribute to standards conformance decisions and recommendations to the AI Domain Committee.

Requirements

8+ years building production software, including time at staff, principal, or architect scope.
Practical experience designing ontologies, knowledge graphs, or canonical domain models that shipped in production.
Hands-on experience with LLM-based or agentic systems.
Experience with fine-tuning, RAG, or model evaluation pipelines.
Hands-on Microsoft Foundry: model deployment, agent development, and its evaluation and safety tooling.
Hands-on Azure: compute, data, identity, and networking building blocks for AI workloads.
Ability to take a pattern from concept through working proof-of-concept to published standard.
A record of changing technical direction through influence rather than authority, across team boundaries.
Clear writing skills for ontology, patterns, and decision records.

Nice To Haves

PEO, HCM, payroll, benefits, or adjacent regulated-domain experience.
Ontology and knowledge-representation tooling (OWL, RDF, SHACL, property graphs) or semantic layer design.
Multi-tenant SaaS handling sensitive personal data, including SOC 2 or ISO 27001 environments.
Agent frameworks, Microsoft Agent Framework in particular, plus MCP and tool-use orchestration.
Snowflake Cortex AI and its integration with broader AI platforms.
Prior AI research experience.
Formal knowledge-engineering credentials.
Domain curiosity.

Responsibilities

Encode domain meaning for AI capabilities.
Own the domain intelligence layer: ontology, agent workflow models, fine-tuning strategy, and intelligence pattern library.
Build proof-of-concepts for new AI patterns.
Develop the canonical ontology as a semantic layer.
Model agentic workflows for business processes.
Define fine-tuning strategies and dataset curation standards.
Create and document an intelligence pattern library.
Engage with product teams from design through go-live.
Advise on use-case feasibility and risk.
Act as an escalation point for domain-AI design questions.
Contribute to standards conformance decisions.