Welcome

Angel Crispin

Software Engineer

Lima, Peru

I design and build scalable software systems that power modern digital products. My passion for clean architecture, sharp algorithms, and meaningful data puts me in a unique place in the engineering world.

By the numbers

0+

Projects completed

0k+

Lines of code written

0+

Technologies applied

Selected work

All work →

GRAMA

AI-focused learning engine and LMS for teacher training across multiple institutions, built for Industrias Roland Print S.A.C. and in production since June 2026. A RAG learning assistant on Google Gemini, MCP integration and auto-generated course content, on top of a hexagonal/DDD modular monolith with a multi-tenant PostgreSQL schema secured by Row Level Security.

Next.js 16TypeScriptSupabasePostgreSQLpgvectorGemini APIMCPTailwind CSS 4Vercelk6
→

Save the Valley

2D sandbox game built from scratch in C++ with a custom engine architecture. Features infinite procedural world generation, multi-weapon combat system, enemy AI with state machines, and optimized chunk-based rendering — all without a game engine.

C++17SFML 2.6CMakeSimplex Noise
→

GestureKey

Real-time hand gesture detection system that translates webcam input into OS-level keyboard shortcuts. Clean layered architecture with an integrated ML pipeline — from raw camera frames to system actions, running as a background tray app.

PythonOpenCVMediaPipeScikit-learnPyQt6
→

I can help you with

01

Full-Stack Development

Building scalable web applications with modern frameworks and architectures. From frontend interfaces to backend systems.

Next.jsTypeScriptNode.js

02

Backend & Architecture

Designing backends that hold up under load: hexagonal architecture, multi-tenant PostgreSQL with Row Level Security, and load-tested APIs.

PostgreSQLSupabaseDDDREST

03

Process Automation

Turning manual, repetitive work into reliable pipelines: web scraping, OCR document extraction, workflow automation and AI-assisted classification.

PythonPlaywrightOCRn8nApps Script

04

Applied AI

Adding AI where it earns its place: RAG assistants grounded in your own content, tool calling, and MCP integrations.

Gemini APIRAGMCPpgvector