AI Full Stack Engineer | AI Systems & Automation

I build AI systems that automate real operations.

I combine FullStack + Data + AI to take products from idea to production with measurable impact. I work with NestJS, Next.js, TypeScript, Python, Airflow, OpenAI and AWS.

AI Systems & AutomationData Pipelines (Airflow)NestJS / Next.js / TypeScript
AI Full Stack Engineer

FullStack + Data + AI.

I do not just ship features: I design systems where backend, frontend, data and AI work as one unit, with type-safe architecture and operational focus.

  • Nest.js / Next.js / TypeScript with type-safe architecture
  • Python + Airflow for pipelines and orchestration
  • OpenAI + AWS + Docker for automation and deployment
Automation

40% support automation

LLM-assisted workflows deployed in production through WhatsApp and tawk.io.

Reliability

25% fewer production errors

Driven by type-safe systems, cleaner interfaces and more resilient architecture.

Performance

20% faster initial load

Improved frontend delivery through scalable components and stronger UI architecture.

Automation

40% support automation

Reliability

25% fewer production errors

Performance

20% faster initial load

Growth

15% more organic traffic

Real profile

AI-driven systems, type-safe architecture and product work with measurable impact.

I am a full stack engineer specialized in AI systems and data pipelines. I design architectures where artificial intelligence is not a feature, but the operational core of the system.

Summary

FullStack + Data + AI to take products from idea to production.

I work with Nest.js, Next.js and TypeScript for product delivery, Python and Airflow for orchestration and pipelines, and OpenAI + AWS + Docker for automation, deployment and scalability.

  • Nest.js / Next.js / TypeScript with type-safe architecture
  • Python + Airflow for pipelines and orchestration
  • OpenAI + AWS + Docker for automation and deployment
Current headline

AI Systems & Automation | NestJS, Next.js, TypeScript, Airflow, OpenAI and AWS

Current location

Greater Mexico City Metropolitan Area, Mexico

Specialization

AI-driven systems, conversational automation and data pipelines

Target roles

AI Full Stack Engineer, AI Systems Engineer and Data + AI Engineer

Production AI, not experimental

I design systems where AI is tied to real operational workflows, especially in conversational automation, support and process execution.

Backend and data rigor

I work across services, APIs, ETL and Python/Airflow pipelines so analytics, automation and product can share a reliable foundation.

Proven impact

I have automated 40% of support operations, reduced production errors by 25%, improved frontend performance by 20% and increased organic traffic by 15%.

Featured projects

Selected case studies that show both interface craft and systems depth.

Each case study combines product context, implementation responsibility and measurable impact, with room for walkthroughs, stills and operational detail.

Product demo
Video

Product demo

Functional demo of the main flow.

Active project

Handbook AI Workflow Automation

Built for real operational workflows: complex processes with handoffs, follow-ups, evidence and SLAs that Handbook turns into guided execution with live dashboards and audit trails.

LLM SystemsProduct ArchitectureOperations
Role

AI Full-Stack Engineer

Company / context

Handbook

Period

Feb 2026 - Present

Problem

Many operations rely on fragmented handoffs, approvals and evidence collection, which creates missed steps, SLA risk and poor visibility.

My role

As an AI Full-Stack Engineer, I work across Product Architecture & LLM Systems to model processes and turn them into guided execution with rules, reminders and escalation paths.

Why it matters

It demonstrates AI applied to real operations in manufacturing, banking and insurance with SLA visibility and complete auditability.

Results and key points
  • Real workflows: procurement, production, collections, document review and claims coordination.
  • Guided execution with live dashboards, evidence capture and end-to-end audit trails.
  • Operational metrics: cycle time, SLA compliance, on-time outcomes and rework reduction.
How I work

From the real operational bottleneck to a system that can hold in production.

Identify the operational bottleneck, design a resilient system, and ship with measurable outcomes.

01

Find the real bottleneck

I start by isolating what is actually slowing the operation down, whether it lives in support, analytics, backend, UI or the handoff between teams and systems.

02

Design the system, not just the surface

The best solutions combine type-safe architecture, thoughtful product flows and integrations that can actually support real usage.

03

Ship with measurable impact

The goal is not only to release, but to leave behind a system that automates, reduces errors, improves performance and can be operated with confidence.

Outcomes

Proven impact in support, stability, performance and conversion.

Measured impact in automation, reliability, performance and product growth.

Automation

40% support automation

LLM-assisted workflows deployed in production through WhatsApp and tawk.io.

Reliability

25% fewer production errors

Driven by type-safe systems, cleaner interfaces and more resilient architecture.

Performance

20% faster initial load

Improved frontend delivery through scalable components and stronger UI architecture.

Growth

15% more organic traffic

Driven by technical SEO improvements, stronger frontend structure and better product quality.

Execution stack

Technologies used, grouped like a technical CV.

Stack organized by key capability areas for AI Full Stack Engineer roles.

Capability

Programming languages

TypeScriptJavaScriptPythonKotlin
Capability

Frontend

ReactNext.jsAngularViteHTML5CSS3Tailwind CSSRedux
Capability

Backend and APIs

Node.jsAPIs RESTAPI designHexagonal architectureDomain-Driven Design (DDD)
Capability

Databases

MongoDBMySQLPostgreSQLMariaDB
Capability

Artificial Intelligence / ML

OpenAI APIClaude APIConvolutional neural networks (CNN)Image processingMachine learning model API integration
Capability

Mobile

FlutterKotlin (Android)
Capability

Tools and DevOps

GitGitHubGitLabAWSDockerVercelCI/CDLinuxnpm / package jsonBasic CLILayered separation (controllers, services, domain)
Credentials

Education, certifications and languages behind the execution.

Relevant education and certifications for product, backend and AI systems roles.

Education

Formal software and programming foundations for designing and maintaining production systems.

  • Software Engineering — Universidad Politecnica de Chiapas
  • Programming Technician — CETIS 138 (2020)

Certifications

The current profile combines UX, cloud and systems/network fundamentals to complement day-to-day full-stack practice.

  • Google UX Design Specialization (2024)
  • AWS Academy Cloud Architecting (2024) and Introduction to Cloud (2024)
  • AWS Academy Cloud Foundations (2022)
  • Cisco: Network Support and Security, Operating Systems Basics and Networking Basics (2024)

Languages and market

Prepared for product teams, startups and remote environments with international expectations.

  • Native Spanish
  • Intermediate English B1, close to B2
  • Open to remote roles and international teams
Verified badges

Official badges verifiable on Credly.

Final CTA

I am looking for roles where AI, backend and frontend are not treated as separate tracks.

I am looking for roles where I can contribute to product architecture, backend, data and AI integration with measurable impact.