LDLet's connect
Healthcare Operations · Data & AI Systems

Operational healthcare systems, engineered from inside the workflow.

9 years inside hospital operations, an MSc in Data Science, and the analytics, AI, and applications clinical teams actually use — SQL, Python, R, Tableau / Power BI, LLM workflows, and full-stack systems on Next.js, FastAPI, and PostgreSQL.

Vancouver, BC · Open to healthcare data, analytics, AI, and application engineering roles — remote, hybrid, or on-site · Currently running a multi-site hospital equipment-tracking and analytics system in production

See the production systemCore capabilities

AI tools

ClaudeOpenAIGeminiCursorGitHub CopilotAntigravity

Stack

SQLPythonRTableauPower BINext.jsTypeScriptFastAPIPostgreSQLPower PlatformMicrosoft ListsQR / barcode workflows

4

Hospital sites · live deployment

800+

Assets under one shared state model

9+

Years in healthcare operations

Aug 2025

Equipment-tracking system live since

Currently available

Vancouver, BC · Open to healthcare data, analytics, AI, and application engineering roles — remote, hybrid, or on-site

Start a conversation

Core capabilities

Built across the stack hospitals run on.

Four capability clusters — built on real clinical operations.

Clinical Operations Intelligence

  • Hospital workflow optimization
  • Rehabilitation operations
  • Equipment tracking systems
  • Operational analytics

Applied AI & Data Systems

  • SQL · Python · R
  • Prompt engineering · LLM workflows
  • Structured data extraction
  • AI-assisted automation

Analytics & Visualization

  • Tableau · Power BI
  • Time-series analytics
  • KPI & operational reporting
  • Data storytelling

Application Development

  • React · Next.js · TypeScript
  • FastAPI · PostgreSQL
  • Cloud deployment
  • Production-grade UX

HOW I WORK WITH AI

An algorithm, not a vibe.
This is the loop I run.

Most data-science workflows stop at a notebook. Mine ships into production because every step has a gate — a spec, a test, a review, an observable system — and AI agents do the heavy work inside those gates.

  1. FRAME — WITH THE OPERATOR. Frame the problem with the operator, not the dataset.
  2. SPEC — DESIGN BEFORE CODE. Write the spec before any code.
  3. PLAN — REVIEWABLE UNITS. Decompose the spec into a reviewable plan.
  4. BUILD — TESTS WITH THE CODE. Build with agents — code and tests produced together, every step reviewable.
  5. VERIFY — MULTI-GATE. Verify against a stack of gates — types, lint, tests, eval/regression, secrets check, human review.
  6. SHIP — RELEASE-TAGGED. Ship with a release tag and a written rollback path.
  7. OBSERVE — LOGS & FEEDBACK. Observe in production — logs, traces, and incident feedback drive the next loop.

Three explicit gates: after SPEC the spec must be clear or work returns to SPEC; after VERIFY the multi-gate check must pass or work returns to PLAN; after OBSERVE production must be healthy or the next loop starts at FRAME.

Featured work

A deliberate progression: real healthcare operations · applied AI & data engineering · enterprise automation · product-engineering breadth.

View all projects
Anchor system · Production deployment
ProductionCase Study

Multi-Site Hospital Equipment Tracking & Analytics System

Production healthcare-operations platform deployed across 4 hospital sites — 800+ tracked assets coordinated through QR / barcode workflows, lifecycle visibility, operational analytics, and real-time chain-of-custody.

  • Multi-site coordination across 4 hospitals
  • QR / barcode workflows for intake, dispatch, and return
  • Operational analytics on utilization, dwell time, and rotation
  • Lifecycle visibility from acquisition to retirement

Power Platform · Microsoft Lists · React · TypeScript · QR / barcode workflows · operational analytics

Read the case study

Deployment flow

Sites
QR Scan
Workflow
Lifecycle DB
Ops Dashboard

4 sites

deployed

800+

assets tracked

Multi-site

coordination

Chain

of custody

APPLIED AI / CLINICAL DOCUMENTATION

Clinical GenAI Agent & Analytics Pipeline

PrototypeAI-AssistedCase Study

AI-assisted rehab documentation pipeline that converts messy dictated therapy notes into structured recovery metrics and analytics-ready data — with validation, audit, and human review built in.

FastAPI, Python, PostgreSQL, LLMs, React, TypeScript
CLOUD AUTOMATION + EVENT-DRIVEN SYSTEMS

Enterprise Healthcare Workflow Automation Engine

PrototypeCase Study

Power Automate flows, Azure Functions, and webhook orchestration wired into the Microsoft 365 ecosystem — built prototypes of the patterns that turn manual hospital handoffs into event-driven workflows.

Power Automate · Azure Functions · webhook orchestration · Microsoft Graph · operational alert systems
FULL-STACK PRODUCT ENGINEERING

SpendWise

PrototypeCase StudyDemo Available

Full-stack product platform demonstrating scalable application architecture, data modeling, and polished UX systems — a deliberate non-healthcare proof point for product-engineering breadth.

React Native, Expo, Node.js, PostgreSQL, Prisma

Let's build the next healthcare system.

I'm running a multi-site hospital equipment-tracking and analytics system in production, and I'm open to healthcare data, analytics, AI, and application engineering roles — remote, hybrid, or on-site. The best way in is a short conversation.

Start a conversation

Find me on