# Ciarán Trevino

> I am an engineer and technical product manager in New York. I build and test AI and edge systems that run in production. I am available part-time now and full-time from January 2027, when my NYU degree is conferred. I am looking for forward deployed engineering and technical product manager roles.

This is a plain-text summary of https://ciaran-trevino.com for language models, search tools and recruiting software. The facts match the page and my resume.

## At a glance

- Name: Ciarán Trevino (also written Ciaran Trevino)
- Location: New York, NY
- Work authorization: US citizen and Irish citizen. No visa sponsorship needed to work in the US or the EU.
- Current roles: Chief Technology Officer at Aqqut (Sep 2025 to now); Technical co-founder at ClearText (2026 to now)
- Education: New York University, School of Professional Studies, Bachelor of Science in Leadership and Management. Coursework complete December 2026; degree conferral January 2027.
- Availability: part-time now, 15 to 25 hours a week; full-time from January 2027
- Looking for: forward deployed engineering and technical product manager roles; agent infrastructure, verification tooling, and deployments that have to survive contact with the real world
- Email: crtmcvino1@gmail.com
- Book a call: https://ciaran-trevino.com/book (30 minutes on Google Meet, Tuesday to Thursday, 11 AM to 4 PM Eastern)
- LinkedIn: https://www.linkedin.com/in/ciaran-trevino
- GitHub: https://github.com/ciaran-png

## Experience

- ClearText, Technical co-founder, New York, 2026 to now. 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.
- Aqqut, CTO, edge AI for the High Arctic, Sep 2025 to now. 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 AI proposes events and never drives equipment. Every event is checked against an AsyncAPI 3.1 contract before it leaves the gateway. I provisioned the RevolutionPi and NVIDIA Jetson for remote bring-up over a private Tailscale mesh. 778 automated tests, CI on both repos, a durable outbox at 96 percent coverage. Python 3.11, MQTT, Azure IoT Hub and Device Twins, RevolutionPi, NVIDIA Jetson, Docker, GitHub Actions. The hardware is staged on site after the annual sealift. The cofounder relationship started in 2025 on a Mars-analog crew on Devon Island, where I was the engineer.
- Communiqué, website and CMS build for a media organization, May 2026 to Sep 2026. I built the website and Wagtail CMS. 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. Django, Wagtail, Docker, Caddy. Built by Ciarán Trevino.
- Wren Education, Frontend developer, Dec 2025 to Mar 2026. I built the frontend for wrened.com, a platform of classroom math activities: React and Vite, live KaTeX math rendering, a markdown activity pipeline, PDF export.
- Rise8, Project intern, remote, Aug 2025 to Sep 2025. I extended an internal AI platform from GitLab CI to GitHub Actions so automated compliance reports ran on both. 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.
- Royal College of Surgeons in Ireland, Technical product manager (internship), Dublin, on site, Jun 2025 to Aug 2025. 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.
- Celestron, Lead developer, intelligent remote observatory project, Aug 2024 to Aug 2025. Real-time satellite pass planning, automated slewing and capture, and a tethering capability that lets one operator coordinate thousands of networked telescopes.
- Space 4 All, Lead developer, automatic satellite imaging project, Dec 2023 to Dec 2024. I automated a New Mexico observatory's dome operations and imaging pipelines.
- Royal College of Surgeons in Ireland, Lead developer, HealthNexAI, remote, Oct 2023 to Dec 2024. A four-module tutor bot for clinicians on GPT-4, with an Azure-hosted avatar for delivery and progress tracking. I owned requirements, testing, and stakeholder enablement.
- Kohl's, Product manager across three stints, San Francisco Bay Area, 2022 to 2024. As product manager I owned product, design, and engineering for an executive chatbot on the ChatGPT API, with vector storage over weekly reports. 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.
- Alex Lowe Charitable Foundation, Project lead, Phortse, Nepal, Sep 2023 to Nov 2023. 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.
- Pivotal Software, Project intern, San Francisco, summer 2018. I paired on production client teams at fourteen, including StubHub, in JavaScript and C++.

## Systems I built for myself

- HQ: the multi-agent system I run my own work on every day. An orchestrator dispatches eight domain agents through custom MCP servers, and every outward action needs my approval first.
- Hearth: a smart-home hub where the AI never claims an effect it did not witness on two independent channels, and the LLM is never in the device hot path. 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. 377 tests, with milestones proven live on real radios. It includes ESP32 sensors I soldered and flashed myself.
- ClearCheck: 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. A 200-probe suite runs daily in CI against pinned model endpoints, with evidence committed since July 16, 2026. In the method's proof benchmark, 11 of 11 preregistered thresholds passed, independently replicated. Changes in a model's answers are scored with exact McNemar tests under Bonferroni correction.
- Argot Layer: a semantic translation layer for enterprise SaaS that finds the fields APIs silently drop. 404K rows across 47 tables from 150+ public sources.

## San Francisco, October 2025

- I organized a permitted, closed three-mile skate route from Christmas Tree Point through Noe Valley into the Castro. City permits came from ISCOTT, SFMTA and the Entertainment Commission. 100+ riders, 25 radio-equipped spotters, medics staged, 60+ organizations, no injuries, zero arrests. The San Francisco Chronicle covered it on October 10 and October 11, 2025. Free copies: https://www.yahoo.com/news/articles/f-skateboarders-ditch-dolores-plan-214139464.html and https://www.yahoo.com/news/articles/f-skateboarders-transform-hill-bomb-232005545.html

## Skills

- Languages: Python, JavaScript, C++, PHP, SQL
- AI: LLM evaluation, retrieval-augmented generation, MCP servers, multi-agent orchestration, prompt engineering, OpenAI and Anthropic APIs
- Cloud and infrastructure: Azure (AI Search, Document Intelligence, Blob Storage, IoT Hub, Device Twins), Docker, GitHub Actions, Tailscale, Caddy, systemd
- Web: React, Vite, Vue, FastAPI, Django, Wagtail, aiohttp, Playwright, HTML and CSS
- IoT and hardware: MQTT, Modbus, BLE, Zigbee, ESPHome on ESP32, RTL-SDR, Home Assistant, RevolutionPi, NVIDIA Jetson, Raspberry Pi
- Space: satellite pass planning, telescope and dome automation
- Product: discovery through delivery, outcome roadmaps, user research, Agile and Scrum, executive presentation

## Links

- [Website](https://ciaran-trevino.com/): the full page, newest work first
- [Book a call](https://ciaran-trevino.com/book): pick a 30-minute slot
- [Resume (PDF)](https://ciaran-trevino.com/Ciaran_Trevino_Resume.pdf)
- [LinkedIn](https://www.linkedin.com/in/ciaran-trevino)
- [GitHub](https://github.com/ciaran-png)