Building AI-powered products involves knowing when to delegate routine tasks to AI and when to develop them personally.
I'm JC, founder of Primo Engineering. I ship full-stack, mobile, and cloud systems where the model proposes and deterministic code disposes.
Build something with me
AI product engineering, cloud infrastructure, and full-stack and mobile apps, from a blank repo to a shipped product.
See what I doYou're hiring
A software, cloud, and AI engineer with shipping, multi-platform, and infrastructure experience. See the projects, stack, and résumé.
View experienceHelpful apps and tools built and shipped
- AI · Python
Marina Method
An AI study-guide pipeline built on one rule: the LLM proposes, deterministic code disposes. Bloom classification, citation verification, and mode routing run as plain code that cannot hallucinate.
FastAPI · Python 3.12 · SQLAlchemy · ClaudePrivate · available on requestView more - Product · Multi-platform
Bitácora
A bilingual (EN/ES) behavioral-incident platform for schools. Teachers speak; AI transcribes and structures the report. Ships on iOS, Android, and a React ops dashboard with agent orchestration.
SwiftUI · Kotlin/Compose · React · Express · WhisperPrivate · available on requestView more - Ops · Full-stack
PE Operations Control
The internal ops center for the Primo Engineering agent pipeline. Real-time visibility across tickets, QA, AI cost, and agent jobs. Built it because running a team of AI agents without it is not manageable.
React · Express · SQLite · Docker · ClaudePrivate · available on requestView more - Cloud · DevOps
Employee Onboarding Infra
An idempotent serverless onboarding API: call it a thousand times for the same person and exactly one record is written. Least-privilege IAM, X-Ray tracing, multi-environment.
Terraform · Lambda · DynamoDB · Cognito · SESView more
From the model to the metal
One engineer across the whole stack: AI pipelines, cloud infrastructure, web, and mobile, with the same bar for rigor at every layer.
AI Product Engineering
LLM pipelines that fail safe, not confident. The model proposes; deterministic, auditable code disposes.
Cloud & Infrastructure
Idempotent infrastructure as code on AWS: Terraform, Lambda, DynamoDB, Cognito, and API Gateway.
Full-Stack Product
End-to-end web apps: React and Vite front ends on Express or FastAPI APIs with SQLite or DynamoDB.
Mobile Apps
Native iOS in SwiftUI/SwiftData and Android in Kotlin/Jetpack Compose. Voice-first and offline-capable.
Agent Orchestration
Dispatching AI agents as sandboxed containers, with ops dashboards, job queues, and live telemetry.
Quality & Testing
Large automated suites, Playwright end-to-end tests, and CI that refuses to ship on a silent failure.
Julio "JC" Primo
Software, cloud, and AI engineer, and the founder of Primo Engineering. I build production systems where large language models do the one thing they're good at, reading and proposing, while deterministic, auditable code verifies everything that has to be correct.
Recent work spans an AI study-guide pipeline with 188 automated tests, a bilingual behavioral-reporting platform shipping on iOS, Android, and the web, and idempotent serverless infrastructure on AWS. I work in tight human-AI pairs, with Google-standard code review and every change tracked to a ticket.
Have a project, a role, or an idea? Let's talk.
The fastest way to reach me is GitHub or email. Happy to share private repos, walk through the architecture, or talk about a role.
github.com/jcprimo