Background
A decade making sure
knowledge doesn't get lost.
My career started in libraries and archives — places where organizing, describing, and making knowledge findable is the whole job. What I learned there was that the hard problem isn't storing information; it's giving it enough structure that other people — and now, other systems — can reliably understand and use it.
That thread runs through everything I've done since: building taxonomies at Cisco to govern metadata across enterprise content systems, designing ontologies at Boeing for aerospace knowledge management, and developing the semantic infrastructure at the International Monetary Fund that connected structured financial data across global teams.
The work has always been the same at its core — take complex domain knowledge that lives informally in people's heads or inconsistently across systems, and give it the formal structure it needs to be governed, reused, and trusted.
The field now has a name for what I've been doing — AI grounding — and a genuine shortage of people who know how to do it properly.
What's changed is that the stakes of doing this well have gone up considerably. AI agents operating in finance, healthcare, and regulated industries are only as reliable as the domain knowledge underneath them.
Education
Two graduate degrees.
One in information. One in climate.
My MLIS from the University of Arizona gave me the foundational framework: information architecture, metadata standards, controlled vocabularies, and the theory behind how knowledge gets organized and retrieved.
The second — MS in Climate Science from Northern Arizona University — sharpened something the first didn't: how to work with complex, uncertain, multidisciplinary knowledge and still produce something actionable. Climate science is a domain where the stakes of imprecise terminology are unusually high. That informs how I think about semantic precision in any domain.
MA, Library & Information Science
University of Arizona
Metadata standards · controlled vocabularies · information architecture · knowledge organization
MS, Climate Science & Solutions
Northern Arizona University
Complex domain modeling · scientific data management · multidisciplinary knowledge systems
Industries & Employers
Fortune 500s, federal agencies,
and everyone in between.
The semantic problems at a global technology company are structurally similar to those at a federal financial institution — different vocabularies, same underlying need for governed, interoperable knowledge. Having worked in both means I don't have to learn how large organizations function from scratch.
| Cisco Systems | Metadata Analyst | Enterprise taxonomy governance, Progress Semaphore, metadata standards at Fortune 500 scale |
| Int'l Monetary Fund | IT Metadata Specialist / Taxonomist | Federal-scale ontology design, SharePoint governance, multilingual taxonomy across global teams |
| The Boeing Company | Info Science Specialist / Ontologist | OWL ontology, aerospace knowledge management, semantic interoperability |
| Naval Postgraduate School | Catalog & Metadata Librarian | Bibliographic metadata, cataloging standards, defense research knowledge systems |
| AECOM / Oak Ridge Nat'l Lab | Earlier Roles | Corporate knowledge repositories, scientific data, metadata for engineering and research orgs |
Going Independent
The job market is slow.
The need for this work isn't.
I'm currently available for both consulting engagements and full-time roles. The consulting path grew from a practical observation: the teams building AI products in regulated industries are moving fast, but very few have anyone on staff who understands formal knowledge representation.
My approach is to embed with AI or data teams — usually for a defined engagement — and build the knowledge layer they're missing: a governed taxonomy, a formal ontology, a grounding data model. Something that persists and improves over time rather than being rebuilt from scratch with each new model deployment.
What I'm looking for is work where the semantic layer is taken seriously — not treated as documentation overhead, but as core infrastructure for reliable AI.
How I Work
Principles behind
every engagement.
A taxonomy without stewardship, lifecycle states, and change management isn't an asset — it's technical debt. I build governance in from the start.
SKOS, OWL, FIBO, HL7 — accumulated wisdom about how to make knowledge interoperable across systems. I use them because they work.
Ambiguity in a knowledge model becomes hallucination in an AI system. I push for explicit scope notes, clear boundaries, and defined usage constraints.
A semantically correct artifact nobody uses is a failure. I spend as much time on stakeholder alignment as on formal modeling.