Who is David R. Rintoul?

David R. Rintoul, also known as Dave Rintoul, is an AI Solutions Architect and CISSP-certified security professional based in Abbotsford, British Columbia. He specializes in enterprise AI delivery, local LLMs, secure RAG workflows, and risk governance.

What AI and technical services does David Rintoul offer?

David builds self-hosted and governed AI systems using agentic architectures, Model Context Protocol (MCP), LangGraph, local LLMs via Ollama, RAG semantic search, Docker, Linux, and Python/FastAPI. His work focuses on keeping data on-premises, reducing third-party risk, and producing attributable answers with cited sources.

What certifications does David R. Rintoul hold?

He holds CISSP, CSPO, CAIP, CDMP, AWS Certified AI Practitioner, AWS Certified Cloud Practitioner, Tableau Certified Data Analyst, Alteryx Designer Advanced, and Six Sigma Green Belt credentials.

What industries and organizations has David Rintoul worked with?

He has professional experience at Microsoft, Siemens, Charles Schwab, The Walt Disney Company, Evernorth (Cigna), and WellCare (Centene), as well as operational leadership roles in healthcare and commercial diving.

Does David Rintoul build production AI systems?

Yes. He deployed ML models into production with WellCare's ML Center of Excellence, raised an enterprise data pipeline's load reliability from 65% to 99.9%, and built the foundational graph databases that set the stage for a 25B node/edge graph at Evernorth — along with self-hosted AI systems running in production, including a RAG semantic search demo and the Is It Canadian? classifier.

What live demos and open-source projects are available?

Available work includes a RAG semantic search demo at rag.davidrintoul.info, the Is It Canadian? classifier at canadian.davidrintoul.info, and open-source repositories for Chatbot Concierge, Local AI Stack, and Tableau XML lineage analysis on GitHub.

David “Dave” R. Rintoul, CISSP

AI Solutions Architect • B.A.Sc. Computer Engineering (Waterloo) • I build and ship production AI systems — self-hosted, governed, for high-stakes organizations.

AI · Engineering · Production · Governance

Experience across Microsoft · Siemens · The Walt Disney Company · Charles Schwab · Evernorth (Cigna) · WellCare (Centene)

Measured outcomes 65% → 99.9% data pipeline reliability · competency-based training cut time-to-productivity 8 → 3 months · two-tier engagement model for a 200+ partner program · complex travel research from hours to minutes

AI Systems & Agentic Architectures

MCP & LangGraph Workflows: Agentic pipelines that pull live data so LLM answers stay grounded in real information, countering the three weaknesses of consumer AI: missing context, model hallucination, and stale training data.

A live example is Voyages By Dave, which combines weather, travel advisories, events, and vendor knowledge into one travel research query — turning hours of cross-referencing into minutes.

High-Stakes Governance & Safety

Operational Leadership: Directed compliance and risk management in healthcare and commercial diving, where a missed check has immediate consequences. That discipline informs AI governance under pressure, preventing avoidable mistakes in high-stakes systems.

AI Security Translation: Turn operational discipline into guardrails that keep systems secure and useful. tableau-xml-parse: a Python audit tool that traces Tableau calculated fields back to database columns, so governance can verify schema changes before they break reports.

Global Alliances & Revenue Scaling

Microsoft: Restructured the 200+ partner program for a customer care product, focusing engineering and field investment on strategic partners while maintaining broad ecosystem coverage.
Siemens: Equipped global sales teams and consolidated 3 telephony platforms into 1 while preserving customer functionality and reducing R&D costs. The result: scaled high-value alliances and reduced R&D cost by consolidating platforms, without losing customer functionality or ecosystem coverage.

Local AI Stack

Self-hosted Firecrawl lacks interact and extract — so this stack provides them. One Docker Compose deployment delivers the full foundational suite — interact, map, crawl, scrape, extract, snapshot — via a custom Playwright service and local Ollama model, with SearXNG search and Langfuse observability behind one gateway and an MCP interface. No outbound LLM calls — all on your own hardware.

Open source repo

Is It Canadian?

An evidence-driven checker that vets whether a company is Canadian. An agentic workflow finds the official site, scrapes corporate pages, and a local model classifies strictly from collected evidence. The result: a defensible verdict with a citation trail for every check — grounded in sources, not model memory.

Try It Live · Open source repo

Chatbot Concierge

A self-hosted RAG chatbot that turns any website into a persistent knowledge base. A LangGraph pipeline crawls and chunks the target site with Firecrawl, embeds it into a vector store, and a local Ollama model answers questions strictly from what was collected — every answer attributable to its source. The result: a concierge that knows a website inside-out, running entirely on your own hardware.

Live Demo · Open source repo

Technical Stack & Core Competencies

Python / FastAPI LangGraph MCP Ollama / Local LLMs RAG Vector Search Qdrant · Neo4j · MongoDB Docker Linux / Self-Hosting CI/CD Cloud Security Data Governance Risk Management Business Intelligence Tableau / Alteryx CISSP CAIP CDMP CSPO AWS AI Practitioner Exec Ed: Wharton · IBM · MIT

What colleagues say

Dave supported my teams through a rebuild and new tech evaluation. He was instrumental in building our foundational graph databases — taking load reliability from about 65% to 99.9% — work that became the 25B node/edge graph in use today. Several of his dashboards and visualization models are still in use. Reliable and possessing a vast technical knowledge base, he’d be an asset to any technical organization.

Keith MelilloDirector, Visual Analysis + Presentation at Evernorth; David supported his teams — 2022

I’ve worked with David and can say he’s a really clever software engineer and ML practitioner. He’d be a huge asset for any project or team needing a jolt of technical creativity to jumpstart or catapult the initiative forward. I hope our paths will cross again.

Peer BoernerIT Director, ML Center of Excellence at WellCare; helped David deploy ML models — 2022

Dave consistently took massive piles of data, massaged them into coherency and built insightful models around them. He has always been a source of new ideas and solutions. His reliability and insight made him a fantastic partner.

Laurence MacKenziePrincipal Solutions Architect at Centene; handled infrastructure and schema for David’s solution designs — 2021

Dave has superior knowledge of technology systems and software with a high level of understanding how to apply it in order to reach productive results. His ability to collaborate and produce understandable solutions always exceeds expectations.

Douglas PaceSr. Captain of Marine Operations at The Florida Aquarium; reported to David — 2018

[Dave] took the time to understand how he could help me in my engineering executive role and methodically provided me with all the pieces in the puzzle. I enjoyed his pleasant demeanor and his can-do attitude, as well as his reliable delivery of results. He was a great partner and I would welcome the opportunity to work with him again.

Bill BeydaVice President, Technology and Innovation at Siemens; partnered with David at Microsoft — 2009

[Dave] brought rigor, structure, passion, and a sense of commitment to his role, and earned the respect of his peers and colleagues. An enthusiastic and focused individual.

Vish ThirumurthyDirector of Industry Solutions at Microsoft; managed David — 2008