Available · Seattle — remote or hybrid

Production AIthat ships.

I build human-in-the-loop AI for the users the default system was failing — first as a frontline clinician, now as a technical founder and designer. One USPTO patent pending. One DOI-published pipeline. Ten systems live.

0.985RAG faithfulnessPROVENANCE
83tests · SARIF governance scannerGOVERNANCE-DRIFT · PyPI
55%lower calibration error (ECE)CALIBRATED READINESS
DOIpublished pipeline10.57967/HF/8101
0.985RAG faithfulnessPROVENANCE
83tests · SARIF governance scannerGOVERNANCE-DRIFT · PyPI
55%lower calibration error (ECE)CALIBRATED READINESS
DOIpublished pipeline10.57967/HF/8101
Capabilities

Range and depth,
by deliberate design.

01

Clinical AI

Twenty-one years of clinical, education, and admissions work — anesthesia, psychiatry, special education. Domain depth that informs every system I design.

02

Agentic AI

Production agents on Claude's tool-use API and MCP. ReAct orchestration, multi-step planning, and evaluation harnesses with adversarial test sets.

AB
03

Design-engineering

Working prototypes wired to real systems. Iterative bake-offs with Claude and Cursor, with the visual and interaction craft pushed until it ships.

04

Responsible AI

Fairness audits, bias detection, and SHAP interpretability. Programmatic labeling and weak supervision as production patterns — humans in the loop.

Selected work

Flagship systems first.

Patent-pending clinical AI, a hackathon-shipped agent-governance platform, citation-grounded RAG, and DOI-published research — each solving a specific problem at the intersection of expert domain knowledge and machine intelligence.

Four questions every flagship system here is built to answer.

Governed

Who is allowed to change what, and who approved this change?

Compass-BlackBox IQ

Observable

What did it do, why, and can I reconstruct that later?

GUSS

Evaluated

How do I know it is right, and what is the pass condition?

Provenance

Composed

What are the parts, and are they swappable?

Governance Drift Researcher

01Aug 2026

Governance Drift Researcher

Agent governance · evidence-verified findings · CI gate

Live · PyPI + WeaveMind Cloud

Vendor model lifecycles move; the approved agent inventory doesn't. This scans an Azure AI Foundry catalog against a human-owned baseline and reports the drift under rules that make the report worth trusting: every finding carries its source URI, JSON field path, and content hash, and any finding whose citation no longer resolves is dropped and counted rather than published. Coverage gaps are stated, not implied. It exits nonzero on surviving drift so it works as a CI gate, and emits SARIF for Defender and code scanning. Also ported to Weft and run end-to-end on WeaveMind Cloud, where the human approval gate is structural — there is no API by which the agent can approve its own report.

PythonAzure AI FoundrySARIFWeftGitHub ActionsPyPI
02Aug 2026

Triton Kernel Lab

GPU kernels + compiler IR · study artifacts

Public · CI green on every kernel

Triton kernels — elementwise, softmax, matmul — written to be read as much as run. Each one commits its own lowering artifacts: TTIR, TTGIR, LLVM IR, and PTX, so the compiler's choices are inspectable rather than asserted. Benchmarks put the matmul against a hand-written CUDA C++ baseline and cuBLAS, with the correctness gate bounded by cuBLAS's own error against fp64 rather than an arbitrary tolerance, and softmax against torch.compile's steady state with a committed Dynamo explain artifact. The Jetson bring-up log records six failures in the order they happened, including the one an external cold read caught in the repo's own message.

TritonCUDAPTXLLVM IRPyTorchJetson Orin Nano
03Aug 2026

GUSS

Edge inference appliance · headless + autonomous · solo build

Running · public case study

A governed autonomous agent on 7 watts. A hand-assembled, permanently headless Jetson Orin Nano serving a local Qwen3-8B at 12 tok/s that monitors its own health, restarts its own services, paper-trades a benchmarked portfolio inside code-enforced guardrails, and publishes its own dashboard — twice daily, unattended. The build's core lesson, earned across four documented model failures: code decides, the model narrates. Architecture, ADR-style decision log, and an honest build log in the public case study.

Jetson Orin Nanollama.cppCUDAQwen3-8BsystemdPython
04Jun 2026

Compass-BlackBox IQ

Microsoft Foundry + MCP · solo build

Agents League · AI Skills Fest 2026

A git-backed, Markdown-native blackbox flight recorder and skill auditor for autonomous agents. It governs the layer permissions and orchestration don't — memory and competence. Every action is an immutable decision record; audit heuristics turn uncited decisions into draft skill proposals a human approves. Agents propose; humans promote. Grounds on Microsoft Foundry IQ, kept orthogonal to governed memory.

TypeScriptMCP SDKMicrosoft FoundryFoundry IQsimple-gitObsidian
05Mar 2026

PREVERA Guardian+AI

V-JEPA 2.1 + 3D LIDAR · sole inventor

USPTO PGA-2026-001 · Patent pending

A dual-path agentic fall-prediction pipeline deployed to NVIDIA Jetson Orin. Fast path: under 200ms fall detection. Prediction path: forecasts pre-fall motion 2–3 seconds before impact via a V-JEPA 2.1 encoder/predictor over BEV depth maps. Sensor fusion with LIDAR, pressure mats, and clinical context. HL7 FHIR R4 integration, fairness-audited across mobility and body-type subgroups.

V-JEPA 2.1Jetson OrinPyTorchHL7 FHIR R4SHAP
06May 2026

Provenance

Citation-grounded multimodal RAG · no GPU

Live

Ask a textbook a question; get an answer where every claim is checked against the exact page image that proves it. Retrieval is Cohere Embed v4 over 1,347 page images; answering and verification are Claude vision calls in a LangGraph verify→repair loop. Faithfulness 0.985, recall@5 0.864 — reported as measured, not tuned. Fully API-based and serverless.

Cohere Embed v4Claude visionLangGraphFastAPINext.js
07May 2026

Clinical AI Agent

SMART on FHIR + transparent RAG

Live demo

Patient-grounded, citation-traceable clinical decision support on open standards. A 5-agent pipeline fuses a patient's live SMART on FHIR record with cited evidence, emits dual citations (patient data + literature), and scores its own faithfulness with a built-in Clinical Work IQ harness. Built to fill the unoccupied square in a scan of nine frontier healthcare-AI companies: open, transparent, patient-grounded, self-proving.

SMART on FHIRLangGraphChromaDBGradioClaude
08May 2026

À la Carte

Design-engineering case study · solo

Live

A reading-group companion app — and a working argument that the typed-component pattern from frontier-lab game-playing research generalizes outside of games. Six recipe cards, five lifecycle states, one canonical card catalog that fills session by session. Built end-to-end in a deliberate bake-off with Claude and Cursor. Demonstrates the AutoHarness / Code-World-Models pattern on a non-clinical surface.

ReactClaudeCursorSnorkel FlowFoundry
092025

FetchMerck AI

Published RAG · clinical decision support

DOI 10.57967/hf/8101

An end-to-end RAG pipeline published on Hugging Face with a DOI: ingestion, chunking, embeddings, semantic retrieval, re-ranking, prompt engineering, deployment. LLM-as-a-Judge scoring rubrics across multiple clinical query classes — the evaluation infrastructure is the asset, not the model itself.

Mistral-7BLangChainRAGHugging Face

Also shipped — earlier work & explorations

calibrated-readiness

Calibrated, falsifiable exam-readiness with a 60-second reliability-diagram check. Gradio on Hugging Face — free tier, so it sleeps when idle and wakes in ~25s.

ai-use

A LICENSE-style AI-USE.md declaring how AI touched a project — plus a CI checker that fails when the declaration goes missing or stale.

nexus-neuromirror

Offline-first EEG neurofeedback for the Mind Media NeXus-10: EDF/EDF+ verifier, montage configs, web dashboard. PyPI + live app.

python-tutorial

Interactive in-browser Python data-structures tutorial — real Python executes client-side via Pyodide, zero backend. Live on GitHub Pages.

Healthcare Analytics Dashboard

US chronic disease prevalence — diabetes, obesity, heart disease, inactivity — carried from data prep through interactive visualization. Live dashboard.

RuView

A 280K-line third-party WiFi-CSI pose codebase I audited: built the eval gate that exposed the flagship pose metric as unmeasured, and the ADR recording it. Fork · 66 ADRs · archived.

semantic-scholar-api

Thin client and runnable examples for the Semantic Scholar Academic Graph, Recommendations, and Datasets APIs.

p2pool-monitor

Local-first macOS menu bar + web dashboard for a self-hosted Monero P2Pool rig. Reads your own node and miner; the wallet address never leaves the machine. BSD-3.

Remy V1

Public research & reading-group agent on Hugging Face — free tier, so it sleeps when idle and wakes in ~25s.

llm-council-mcp

Multi-model deliberation (Karpathy-style, 3-stage) as an MCP server. MIT · PyPI.

SuperKart Sales Predictor

scikit-learn Random Forest · RMSE 277.28 · R² 0.9326 · model + Streamlit + Flask.

healthcare-vjepa2-agent

V-JEPA 2 + Claude analyzing medical procedure videos into teaching content.

Hospital Readmission

30-day readmission prediction · XGBoost · SHAP · 0.76 AUC-ROC.

ReneWind Maintenance

Predictive maintenance for wind turbines · TensorFlow.

helmnet

Safety-first helmet detection — VGG-16 transfer learning with threshold analysis tuned for Zero-Harm deployment.

audit-portfolio

Smart-contract security learning log: CTF writeups, contest findings, and vuln-class notes as they land.

ai-content-receipts

Plain-language guide to spotting AI-made photos, video, and voice — and talking about them with your teen. No tech background needed.

Approach

From bedside
to build.

The methodology is the same across every chapter: design the system that lets a real person do something hard, with humans in the loop and the stakes visible.

fhir/observation.txt
1// patient context, pulled live via SMART on FHIR
2GET /Observation?patient=demo-1
3
4[o-a1c]  HbA1c = 8.2 %   -> flag
5[o-egfr] eGFR  = 52      -> flag
6[o-ldl]  LDL   = 110 mg/dL
Verified
By the numbers

Proof, not
promises.

Verified by patents, DOI & live demos
0
USPTO patent pending — sole inventor (PGA-2026-001)
0
Live, publicly reachable systems — demos, packages, dashboards
0 yrs
At the clinical edge — anesthesia, psychiatry, special ed
0/13
Anthropic Academy courses completed
Responsible AI

Responsible by
construction.

Fairness, interpretability, and honest evaluation aren't a compliance afterthought. They're design constraints I build in from the first commit — especially for systems that touch patients.

USPTODOI 10.57967/hf/8101HL7 FHIR R4SMART on FHIRCC BY 4.0

Fairness audits

Subgroup performance checks across mobility and body-type cohorts before anything ships — built into PREVERA Guardian+AI.

Honest evaluation

LLM-as-a-Judge rubrics, a reproducible Clinical Work IQ harness, and scope-and-saturation reporting. Numbers as measured, not tuned.

Interpretability

SHAP attributions, append-only decision records, and dual citations you can verify against the source by eye.

Human-in-the-loop

Agents propose; humans promote. Programmatic labeling and weak supervision with a person in the loop, and revocable memory.

Stack

A practitioner's
toolkit.

Verified through the patents, published research, and shipped systems — not résumé decoration.

Python
Language
TypeScript
Language
SQL
Language
PyTorch
ML / AI
Hugging Face
ML / AI
scikit-learn
ML / AI
XGBoost · SHAP
ML / AI
V-JEPA 2.1
World models
Claude API
LLMs & agents
MCP
LLMs & agents
LangGraph
LLMs & agents
RAG
LLMs & agents
Cohere Embed v4
Retrieval
React · Next.js
Build
FastAPI
Build
Gradio · Streamlit
Build
NVIDIA Jetson Orin
Edge GPU
HL7 FHIR R4
Healthcare
Databricks · Azure
Cloud
Vercel · Docker
Infra
Python
Language
TypeScript
Language
SQL
Language
PyTorch
ML / AI
Hugging Face
ML / AI
scikit-learn
ML / AI
XGBoost · SHAP
ML / AI
V-JEPA 2.1
World models
Claude API
LLMs & agents
MCP
LLMs & agents
LangGraph
LLMs & agents
RAG
LLMs & agents
Cohere Embed v4
Retrieval
React · Next.js
Build
FastAPI
Build
Gradio · Streamlit
Build
NVIDIA Jetson Orin
Edge GPU
HL7 FHIR R4
Healthcare
Databricks · Azure
Cloud
Vercel · Docker
Infra
Vercel · Docker
Infra
Databricks · Azure
Cloud
HL7 FHIR R4
Healthcare
NVIDIA Jetson Orin
Edge GPU
Gradio · Streamlit
Build
FastAPI
Build
React · Next.js
Build
Cohere Embed v4
Retrieval
RAG
LLMs & agents
LangGraph
LLMs & agents
MCP
LLMs & agents
Claude API
LLMs & agents
V-JEPA 2.1
World models
XGBoost · SHAP
ML / AI
scikit-learn
ML / AI
Hugging Face
ML / AI
PyTorch
ML / AI
SQL
Language
TypeScript
Language
Python
Language
Vercel · Docker
Infra
Databricks · Azure
Cloud
HL7 FHIR R4
Healthcare
NVIDIA Jetson Orin
Edge GPU
Gradio · Streamlit
Build
FastAPI
Build
React · Next.js
Build
Cohere Embed v4
Retrieval
RAG
LLMs & agents
LangGraph
LLMs & agents
MCP
LLMs & agents
Claude API
LLMs & agents
V-JEPA 2.1
World models
XGBoost · SHAP
ML / AI
scikit-learn
ML / AI
Hugging Face
ML / AI
PyTorch
ML / AI
SQL
Language
TypeScript
Language
Python
Language
Open source

Built in public.
Runnable, reproducible.

Several systems ship as public, runnable artifacts — MCP servers, Hugging Face Spaces, and DOI-published pipelines. Reproducible from the repo and gated by offline tests.

MCP-native

Two MCP servers — llm-council and Compass — callable from Claude Code.

Reproducible evals

Offline CI gates, golden sets, and honest scorecards in every repo.

Live demos

Runnable Hugging Face Spaces and Vercel deployments, not screenshots.

DOI-published

Citable research — DOI 10.57967/hf/8101.

# multi-model deliberation, from Claude Code
claude mcp add llm-council \
  --env OPENROUTER_API_KEY=sk-or-... \
  -- llm-council-mcp
> council_deliberate("ship v1 Friday?")
# 3 YES / 1 NO -> chairman synthesis
Journey

A non-linear path with through-line.

Every role taught something that compounds in the AI work: clinical reasoning under pressure, mixed-methods research, multi-stakeholder delivery, and consultative communication with expert and non-expert audiences alike.

2024 — Present

Technical Founder · PREVERA Guardian+AI

Independent · Remote

Shipped ten AI applications zero-to-one, with one USPTO provisional filed as sole inventor — all on Claude's tool-use API. Full ownership: research, architecture, deployment, evaluation, patent prosecution. Advisory engagement with The Gerontechnology Group on ethical AI for aging populations. Most recently: Governance Drift Researcher (published to PyPI with trusted publishing and a clean-room wheel test) and Triton Kernel Lab. Earlier: À la Carte and Compass-BlackBox IQ (Agents League @ AI Skills Fest 2026).

2019 — 2024

Special Education Teacher

Hawai'i Department of Education

Designed data-driven experimental interventions for 20+ students per year — mixed-methods research with iterative calibration under tight timelines and real stakes. Coordinated cross-functional IEP teams: the literal lifecycle-state-refinement loop À la Carte's architecture is modeled on.

2016 — 2019

Associate Director of Admission & Adjunct Faculty

Hawai'i Pacific University

Consultative delivery at scale: understood objectives, designed academic solutions across programs, navigated multi-stakeholder decisions, and drove outcomes against quarterly targets. Taught research methods as adjunct psychology faculty.

2011 — 2016

Special Education Teacher

Hawai'i Department of Education

First five-year stretch of IEP portfolio delivery across diverse classroom contexts, coordinating cross-functional teams under legally binding targets.

2003 — 2011

Anesthesia & Psychiatric Technician

Queen's Medical Center · Level I Trauma Center

Eight years of frontline clinical reasoning under uncertainty — perioperative workflows, malignant hyperthermia response, psychiatric stabilization. The domain foundation under every AI system I now build.

Credentials

The training behind the work.

Graduate research methodology, frontier AI training, and cloud fundamentals — the foundation for every system I ship.

UT Austin · McCombsMay 2026

Post Graduate Program in AI/ML

Great Learning · McCombs School of Business · GPA 3.95

AnthropicCertified

Anthropic Academy — 13/13 Courses

Claude API, prompt engineering, agentic systems

AMDCertified

AI Developer Path — Agents 101 & 201

Agent architectures on accelerated inference

MicrosoftCertified

Azure AZ-900 & AI-900

Cloud fundamentals · ML, computer vision, NLP, generative AI

DatabricksCertified

Advanced MLOps & SQL Analytics

Machine learning operations and SQL analytics badges

USPTOProvisional filed

Patent Filing — Sole Inventor

PGA-2026-001 · LIDAR + V-JEPA 2.1 fall-prediction architecture

Saybrook UniversityDissertation stage

PhD ABD — Integrative Mind-Body Medicine

Classic Grounded Theory methodology

Chaminade University of HonoluluCompleted

MS Counseling Psychology · BA Psychology

BA Magna Cum Laude

AAPB · BCIACertified

Biofeedback Certification

Biofeedback Certification International Alliance · applied psychophysiology

Contact

Let's build something
that matters.

Open to roles at frontier AI labs and healthcare AI companies — remote, or relocating to SF or Seattle. Also open to advisory and consulting at the intersection of clinical AI, evaluation, and human-in-the-loop product design.

Applied AI EngineerResearch EngineerStaff / Senior Product DesignerSolutions ArchitectAI Engagement

Based in Seattle, WA · Honolulu & SF · UTC−7