Data & Automation Engineer

I build AI agents and automations that kill manual work.

Lucas Ruiz is a data and automation engineer who builds software that removes manual work from data-heavy industrial projects. He works as a data specialist on large-scale industrial commissioning, and he co-authored a peer-reviewed paper on a YOLO-based PPE monitoring system, published in the Proceedings of the Computer Vision Conference (CVC) 2026. Field engineer who builds, builder who has worked the field.

Mining project rotations · open to roles anywhereEnglish & Spanish

See my projects

Who I am

I build AI agents and automations that remove manual work from data-heavy industrial projects. Right now I work as a data specialist on large-scale industrial commissioning: 1,300+ subsystems, 14,000 equipment tags, 13,000+ checksheets. The job is full of repetitive, high-stakes data work: pulling records, validating them, formatting reports, signing off readiness packages. So I automate it.

What makes the combination uncommon is the bridge. I have spent years on real industrial and commissioning sites across the U.S., Canada, Indonesia, and Peru, reading P&IDs, QC-ing equipment packages, owning the data nobody else wants to touch. I also build software. Most people in industrial data ops do not build, and most people who build have never seen a field. I do both, which means the automations I write actually fit how the work happens.

Currently

Large-scale industrial commissioning
14,000 equipment tags
Triathlon Worlds 2026

Experience

Where I've worked

CMS / PIMS Data Specialist (Project Engineer)
Dec 2022 - Present
Commissioning contractor · Salt Lake City, UT (HQ)
One continuous position: joined as an Engineering Intern, then Project Engineer across five internal and site projects, and since October 2025 the CMS / PIMS Data Specialist on a large-scale mining expansion in Indonesia.
1. Mining expansion, Indonesia
  Oct 2025 - Present
  Engineering data management on the client's PIMS platform: validated and uploaded 10,000+ equipment and instrument records, built Python and Playwright automations that replaced manual data collection, and served as the team's primary PIMS point of contact.
2. Resource Loading Tool
  Feb 2025 - Jun 2025
  A two-file Excel system that tracks resource allocation across projects and provisions availability data for each new team with no manual setup. Power Query M keeps the master sheet current, and dashboards let team leads watch workload and capacity across 50+ personnel.
3. SharePoint Document Management System
  Dec 2024 - Apr 2025
  Evaluated Egnyte, OneDrive and SharePoint, then implemented SharePoint as the company's document control platform: controlled libraries, metadata schemas, multi-stage approvals, and Power Automate lifecycle flows wired into Teams.
4. Salesforce Configuration (PM+ App)
  Dec 2024 - Apr 2025
  Configured profiles, views and permissions for the internal project coordination app built on Salesforce PM+, then wrote the onboarding documentation and task-tracking automations that got the team onto it.
5. Cloud Application Development
  Jan 2024 - Dec 2024
  Led end-to-end development of a cloud-based internal app with Power Apps, Power Automate and Azure SQL, selected after evaluating low-code platforms, schema designed in Vertabelo.
6. Gold mining project, Canada
  Jul 2023 - Jul 2024
  Produced and QC'd equipment work packages for mining instrumentation, verifying accuracy against P&IDs and scope-of-work documents, and built Excel and Word templates to standardize the workflow.
7. Copper mining project, Utah
  Dec 2022 - Dec 2023
  Assembled and QC'd checklist packages for mining equipment commissioning, coordinating with the team to meet client delivery deadlines.

Project dates overlap because several ran concurrently inside the one position.

B.S. Software Engineering

Universidad Peruana de Ciencias Aplicadas (UPC) · Lima, Peru

2021 - 2025

Research

Published research

Academic work from my time at UPC, published and peer-reviewed.

Cover of Proceedings of the Computer Vision Conference (CVC) 2026, Volume 3

Conference paper

Mobile Application Utilizing YOLO for Analysis and Monitoring of PPE Usage in a Manufacturing Plant in Lima

Lucas Ruiz, Oliver Tuesta, Abel Rosales

Proceedings of the Computer Vision Conference (CVC) 2026, Volume 3 · pp. 38-53 · 03 June 2026

A mobile application using computer vision (YOLO) to analyze and monitor whether workers on a manufacturing floor are wearing their required personal protective equipment (PPE). The result of roughly a year of R&D and real-plant testing in Lima, Peru.

Tools & skills

AI & Agents

Claude
Claude Agent SDK
LLMs
AI Agents
Prompt Engineering
RAG

Automation & Scripting

Python
Playwright
Web Scraping
Power Query M
Power Automate
Power Apps
Power FX

Data & Platforms

PIMS (omega 365)
Azure SQL
PostgreSQL
Supabase
ETL
Data Validation

Web & Tooling

Next.js
TypeScript
Plaid
Git / GitHub
Vercel
SharePoint

Fluent in English & Spanish. Effective across time zones and cultures.

Selected work

Featured builds

The flagship and two more that prove the niche: software that takes manual, high-stakes data work off people's hands. The rest of the shelf is one click away.

Industrial commissioning automation

Flagship

Large industrial project · field case study

A body of automations that turned the commissioning paperwork into software.

On a large minerals-processing expansion, my day was repetitive, high-stakes data work across 1,300+ subsystems and 14,000 equipment tags. I built a toolkit of automations plus an AI assistant that runs them. The biggest single win took the energization documents from typed by hand to generated from a template.

See how it works

Amaru

Personal AI assistant · v2, in daily use

A voice-first assistant with specialist agents behind a router.

A Next.js progressive web app, a Node worker running a queue of specialist agents behind a router, and a Postgres schema underneath, running unattended. Training, money, career and notes each get their own agent, and the arithmetic they need is done in SQL and handed to them, so an agent chooses and never has to remember. Otto was v1. This is what I use now.

See how it works

Financial Dashboard

finance.qori.land

A production data pipeline with an AI layer on real money.

Plaid pulls real transactions from multiple banks, Claude analyzes spending, and Supabase stores everything behind row-level security. A real, secure, multi-user data product with AI on top, not a toy demo.

Try it live GitHub

See all projects

Beyond work

What I do when I'm not building

The same approach I bring to work: structured preparation, resilience under pressure, and a drive to keep improving.

Triathlon

Qualified for the Age Group World Triathlon Championship 2026 in Spain. Regional race wins in Peru.

Endurance

Half Ironman and a full marathon, structured preparation and resilience under pressure.

Enduro MTB

Competitive enduro mountain biking when the terrain allows.

Snowboarding

Off-season on the mountain. Still chasing the same drive to improve.

I build AI agents and automations that kill manual workkill manual work.