I ship systems in places software is not supposed to work. A Sherpa village in Nepal. A hospital in Dublin. A sealift crate bound for the High Arctic. A closed three-mile street in San Francisco.
Forward deployed engineer and technical product managerPart-time now, full-time from January 2027
10 roles since age 14 3 patent filings pending 778 tests on Arctic edge AI 2 San Francisco Chronicle features
I'm an engineer and technical product manager in New York. I started pairing on production client teams at Pivotal Labs in 2018, when I was fourteen. At Kohl's I shipped an executive chatbot the company still runs. At Rise8 I built compliance automation that cut 40+ hours of writing to under 10 minutes. In Dublin I shipped clinical AI on site. Today I am CTO of Aqqut, where I build edge AI for the High Arctic. I am also technical co-founder of ClearText. I finish my NYU coursework in December 2026, and my degree is conferred in January 2027. I want to work embedded with a customer and own the result in production.
2026 – nowClearText
Technical co-founder · New York
I am sole inventor on three patent-pending filings: ghost-field detection for the Argot layer, and two for recovering latent structure from identifiers assumed to be random, using public observation alone. I write kill criteria before every build. Every claim has to be falsifiable. I killed one product line when it failed its own gates.
3 patent filings pending · sole inventor
AqqutSep 2025 – now
CTO · edge AI for the High Arctic
I run the software side end to end: an industrial gateway whose store-and-forward egress survives satellite outages and power cycles at a site nobody can walk over to reboot. The hardware rides a once-a-year sealift, so the software has to be right the first time. The AI proposes events and never drives equipment. Every event is checked against an AsyncAPI 3.1 contract before it leaves the gateway. The cofounder relationship started in 2025 on a Mars-analog crew on Devon Island, where I was the engineer.
778 tests · CI on both repos · staged after the sealift
May – Sep 2026Communiqué
Website and CMS build · Wagtail on a VPS
I built the website and Wagtail CMS for Communiqué, a media organization. I rebuilt the editor so editors cannot delete pages, unpublish the homepage, or change a page's slug. I cut the homepage edit form by 97 percent, from 31,129 pixels of scroll to 810. The published page stayed byte-identical through the rebuild. I added its first test suite.
built by Ciarán Trevino · Django, Wagtail, Docker, Caddy
Dec 2025 – Mar 2026
Frontend developer · now live at wrened.com
I built the frontend for a platform of classroom math activities and the teaching moves behind them: React and Vite, live KaTeX math rendering, a markdown activity pipeline, PDF export of generated activities. I prototyped the original activity engine before the production rewrite.
launched publicly in 2026
The San Francisco Chronicle covered it twice. I organized it: a closed three-mile route from Christmas Tree Point through Noe Valley into the Castro, staffed like a deployment.
San Francisco Chronicle
The preview. After years of injuries and confrontations at Dolores, the Chronicle reported that "a group of skaters will hold a separate event Saturday on Twin Peaks," and walked through the plan I brought: permits, a safety plan the city signed off on, spotters with radios, medics on standby.
Read the article ↗ Free copy ↗San Francisco Chronicle
The day of. The paper described "a gathering that avoided the injuries and police confrontations of the past," named me as the organizer who conceived it, and quoted the speech I gave from Christmas Tree Point before the first drop.
Read the article ↗ Free copy ↗
"We're definitely trying to fill a void."
Aug – Sep 2025
Project intern · remote
I extended an internal AI platform from GitLab CI to GitHub Actions so automated compliance reports ran on both. Audit-ready documentation took under 10 minutes instead of 40+ hours of manual writing. My PR merged to production. I also built a Product Coach Agent, an LLM evaluator tuned to 3.6 percent coefficient-of-variation consistency with chain-of-thought prompting and calibration anchors. Repeated gradings of the same work agreed instead of drifting.
40+ hours to under 10 minutes · merged to production
Jun – Aug 2025RCSI
Technical product manager (internship) · Dublin, on site
On site in Dublin I built the Clinical Skills Agent, a multimodal retrieval system for clinical education on Azure AI Search, Document Intelligence, FastAPI, and Vue. My LLM-driven build workflow cut spec-to-production time by roughly 90 percent, with mandatory review and human oversight as hard gates.
clinical AI shipped on site · spec-to-production time cut about 90 percent
Aug 2024 – Aug 2025
Lead developer · intelligent remote observatories
I built the intelligent remote observatory stack: real-time satellite pass planning, automated slewing and capture, and a tethering capability that lets one operator coordinate thousands of networked telescopes. From December 2023 to December 2024 I was also lead developer at Space 4 All, where I automated a New Mexico observatory's dome operations and imaging pipelines.
thousands of telescopes, one operator
Oct 2023 – Dec 2024RCSI
Lead developer, HealthNexAI · remote, Ireland
I led an AI education platform for clinicians from concept to deployment: a four-module tutor bot on GPT-4 with an Azure-hosted avatar experience for delivery and progress tracking. I owned requirements, testing, and stakeholder enablement. It bridged working clinicians to AI tooling they actually used.
led concept to deployment · 15 months
2022 – 2024
Product manager, three stints · San Francisco Bay Area
As product manager I owned product, design, and engineering for an executive chatbot built on the ChatGPT API. It still answers leadership questions more than two years after I rolled off. As an intern I led Kohl's OpenAI onboarding, working directly with the OpenAI team. On Marketplace Returns, packages arriving without return slips were costing tens of thousands of dollars; I proposed a back-tracking method, and it cleared a blocker for scaling other Marketplace features. I presented the findings to more than 1,000 employees and executives.
exec chatbot 2+ years in production
Sep – Nov 2023
Phortse, Nepal
Project lead · Khumbu, Nepal
I lived on site in Phortse, a Sherpa village at 12,500 feet. I ran two months of needs assessment on the ground so the design matched local clinical priorities. I co-designed a community hospital and a waste-line system that improved water safety, coordinating charity: water, Action for Nepal, NEWAH, and local partners.
hospital and waterline co-designed on site
Summer 2018
Project intern · San Francisco
I paired on production client teams at fourteen, including StubHub, inside Pivotal Labs' XP culture. There I learned outcome roadmaps and user research.
client delivery in JavaScript and C++
Agent operations
The multi-agent system I run my own work on every day: an orchestrator dispatching eight domain agents through custom MCP servers, a permission gate on every outward action, and control surfaces that are physical (a gamepad that drives a projected wall board), remote (a two-way iMessage channel), and spoken (a wake-word satellite).
8 domain agents · 15+ tool subsystems
zero ungated outward actions, by standing rule
Agent-native hardware
A smart-home hub where the AI never claims an effect it did not witness on two independent channels. Every actuation returns graded evidence, and a bare write acknowledgment counts as failure. The strongest proof that a device is mine is a power cycle the hub witnesses: its radio goes dark and comes back. That proof cannot be forged over the air. Census data is treated as untrusted input. The LLM is never in the device hot path.
377 tests · milestones proven live on real radios
21 devices re-recognized at 1.00 confidence, zero LLM tokens
live hub: 1,235 entities · 167 devices
ESP32 sensors I soldered and flashed
AI verification
It checks every day whether an AI model's answers have changed, with the pass and fail rules fixed before any result exists. Hypotheses and pass thresholds are frozen to SHA-256 before any result exists, every artifact is content-addressed, and an independent auditor can re-verify every verdict hash by hash.
200-probe suite · run daily in CI against pinned model endpoints since July 16, 2026
RFC 3161 timestamp witness on every run
proof benchmark: 11 of 11 preregistered thresholds GO · independently replicated
changes in a model's answers scored with exact McNemar tests, Bonferroni-corrected
Applied research
A semantic translation layer for enterprise SaaS that catches the fields APIs silently drop: build an independent reference corpus of what should exist, diff it against what the tenant actually returns.
404K rows · 47 tables · 150+ public sources
ghost-field detection patent filed Feb 2026, sole inventor
New York University, School of Professional Studies
Bachelor of Science, Leadership and Management
Coursework complete December 2026
Degree conferral January 2027
I am in New York, looking for forward deployed engineering and technical product manager roles: embedded with a customer, writing code on their real problems. I can work 15 to 25 hours a week now and full-time from January 2027, when my NYU degree is conferred. I am a US and Irish citizen, so I need no visa sponsorship to work in the US or the EU. If you are building agent infrastructure, verification tooling, or deployments that have to survive contact with the real world, I would like to talk.