Bruno Gutiérrez
Mexico City · CDMX

AI Engineer · Builder

I build agentic AI systems
and real-time voice products.

I design and ship end-to-end AI products — multi-agent pipelines, real-time voice, and the web apps around them. Below is some selected work.

Bruno Gutiérrez

Selected work

Cinema Pipeline

An AI pipeline that produces cinematic CDMX shorts

In progress

An AI pipeline that produces a complete cinematic world set in Mexico City — original characters, locations, storyboards and short films. Every character, street and frame inside was generated by the pipeline. Meet the cast.

PythonGoogle ADKGemini 2.5Imagen 4Generative videoMulti-agent pipeline

English Circle

An AI English-conversation tutor for Mexican Spanish speakers

Live

Live group voice classes with “Alex,” an AI teacher you actually talk to. Alex replies in natural spoken English in well under a second, understands Mexican slang, corrects you gently without breaking your flow, and sends a personal report after every class.

PythonGoogle ADKGemini 2.5LiveKitNext.jsRailway

Real-Guitar Music Game

Play Mexican music on a real guitar

In progress

Plug a real guitar into your computer and play along to Mexican music. It listens to what you actually play — detecting your chords in real time — scrolls a rhythm lane, shows finger positions, and the crowd reacts as you nail the changes.

PythonPygameReal-time audio DSPChord detectionSQLite

MUXIC Studio

An AI studio that writes and produces original Mexico City music

In progress

From a raw feeling or a few lines of testimony, it crafts complete original songs — lyrics and music — that sound authentically chilango. Built to range across genres: ska, emo, rock and darkwave. Listen to a few of the tracks inside.

PythonGenerative AIMulti-agent pipelineMusic generationNext.js

PhD Research — The Moving Firefighter Problem

Optimization & deep reinforcement learning for fire containment

Published

My doctoral work: a novel graph-theory model for fire spread and containment, solved two ways — exact mathematical optimization (MIQCP) and deep reinforcement learning — then compared head to head. Published, peer-reviewed.

PythonReinforcement LearningMathematical OptimizationMIQCPCellular Automata