Angel Lopez

AI Engineer (GenAI) · Enterprise Search · RAG
Mexico · agdaniel019@gmail.com

I'm an AI Engineer specializing in GenAI and enterprise search, with a Data Engineering background, AWS knowledge, conversational English, and 2 years of experience as a software developer. I build production-ready RAG and agentic systems using Python, Django, embeddings, and vector databases, with a focus on creating reliable automation and AI-powered workflows for SaaS applications and corporations.

Projects

Compey

Automated SPEI Payment Verification Platform

Jan – Apr 2026

Built an AI-powered web platform that extracts key data from SPEI receipts and validates payments against Banxico CEP to support faster reconciliation.

  • Implemented batch processing, duplicate detection, audit logs, verification statuses, and asynchronous OCR/validation workflows using Celery and Redis.
Python Django OpenAI Vision/OCR Celery Redis PostgreSQL Docker Dokploy Hetzner
Website Open demo (video)
Video demo

Cerasyn

Phytoplankton Classification Web App

Apr – May 2026

Developed and deployed an AI-powered web app for phytoplankton image classification using a fine-tuned InceptionV3 model.

  • Reduced classification time from hours to seconds and won the ANUIES 2025 Mexican National Prototypes competition.

Winner, ANUIES 2025 Mexican National Prototypes competition (Mexico).

Python TensorFlow InceptionV3 Anvil Hugging Face Spaces
Website Open demo (video)
Video demo

Academic projects

Phytoplankton Classifier

Thesis project · CNN · Transfer Learning

Live demo of the Anvil platform classifying phytoplankton
Platform in action (Anvil)
CNN results matrix
CNN results matrix
  • Specialized CNN via fine-tuning of InceptionV3, trained on ~580,000 microscopy images to classify phytoplankton genera automatically.
  • Reduced manual classification from hours to seconds, letting university students process full batches through an Anvil web interface without ML expertise.
  • National winner ANUIES 2025 — presented as a working prototype at the national university competition.
Python TensorFlow Keras InceptionV3 Anvil
GitHub Demo

Phytoplankton Image Dataset

Data pipeline · Web Scraping with Selenium · ML dataset

Dataset organized by phytoplankton genus
Dataset organized by genus
Scraping results and CSV consolidation
Scraping results (CSV)
  • Selenium bot to collect ~600,000 images from IFCB Dashboard and PlanktonNet, organized by taxonomic genus in ~40 minutes — work that would have taken days manually.
  • Purpose-built dataset for training the Phytoplankton Classifier CNN; without this data pipeline, that project would not have been feasible.
Python Selenium Google Colab Requests Pandas
GitHub

WebScraperHotels

Prospecting tool · Web Scraping · Terminal

Hotel search result showing extracted contact data
Single hotel lookup
Bulk hotel data extraction process in terminal
Bulk extraction in terminal
  • Terminal-based tool that scrapes hotel listings across multiple directories, extracting name, phone, address, and contact details — consolidated into CSV/Excel automatically.
  • Eliminated manual site-by-site search and data entry, cutting client prospecting time from ~2 hours to under 5 minutes.
Python BeautifulSoup Pandas Requests
GitHub

Experience

AI Developer

WispHub
GenAI Agentic Systems RAG Production
January 2025 – Present

Built AI functionalities inside the CRM for support and sales teams. Developed agents that execute tools (tool/function-calling) and use RAG to respond with context from the internal knowledge base, reducing response times and improving support quality at scale.

~100
companies adopted self-serve AI features
70%
reduction in first-response time
80%
users reported process improvement (surveys)
~$5
/ 2,000 msgs — cost model for pricing
What I Built
  • Agentic workflows with PydanticAI + tool/function-calling
  • RAG pipeline with internal knowledge base (pgvector + PostgreSQL)
  • Self-serve flow builder to configure agents without code
  • Sales agents to automate first response and lead prioritization
How I Did It
  • Python + Django / FastAPI + Pydantic
  • OpenAI / Gemini (embeddings and completions)
  • Postgres/pgvector as vector store
  • Linux (DigitalOcean) + Supervisor for deployment
  • Structured output validation
AI agent workflow architecture diagram
Agent architecture: message → RAG → decision → response / workflow
Live AI agent interaction via WhatsApp
Agent responding to customer via WhatsApp
Agent configuration interface in CRMinbox
Self-serve agent configuration in CRMinbox

How we measured impact

Post-interaction satisfaction surveys, first-response times logged in the CRM, and flow adoption rate per company (internal platform data).

Cost considerations

~$5 USD per 2,000 messages estimated considering embedding + completion tokens (OpenAI/Gemini). Enables defining customer tiers and pricing decisions.

Deployment

Infrastructure on DigitalOcean (Linux), process management with Supervisor to keep workers active, Docker to isolate services and enable zero-downtime updates.

Screenshots shown with anonymized or illustrative data.

Web Developer (Intern)

Volkswagen Cancún

Cancún, Quintana Roo, Mexico

  • Contributed to the design and development of an inventory management system for the IT department.
  • Built a full-stack solution using MongoDB, SQL, React, and Express.
  • Database management, design, and implementation.

  • MongoDB

  • SQL

  • React

  • Express

December 2024 – January 2025

Database Assistant (Intern)

Municipal Secretariat of Public Security and Transit
  • Implemented ETL processes to clean and update the licensing database using DynamoDB in AWS
  • Automated data cleaning and report generation tasks

  • DynamoDB

  • AWS

December 2023 - January 2024

Marketing Developer (Intern)

Zavia ERP
  • Designed and fully developed application to search for potential client information
  • Enabled retrieving client data for sales in seconds

  • Python

  • Customtkinter

  • Pandas

  • BeautifulSoup

September 2023 - November 2023

Marketing Developer (Intern)

Zavia ERP
  • Developed application using web scraping techniques to extract hotel information
  • Facilitated data storage and analysis in CSV and Excel formats

  • Python

  • Requests

  • Pandas

  • BeautifulSoup

  • Numpy

  • Jellyfish

  • Openxlsx

June 2023 - August 2023

Education

Universidad del Caribe

Bachelor's Degree in Engineering
Data Engineering and Organizational Intelligence

Final Grade: 9.23/10

Top GPA in the program

August 2020 - January 2025

Colegio Boston Tikal

High School

Final Grade: 9/10

September 2018 - August 2020

Skills

AI/GenAI

OpenAI Gemini LangChain LangGraph PydanticAI RAG pgvector Chroma

Backend

Python Django FastAPI REST Docker

Data

Postgres MySQL DynamoDB ETL/ELT

Infra

Linux Hetzner Supervisor AWS (EC2/S3/IAM)
Programming Languages & Tools

  • Python

  • TensorFlow

  • FastAPI

  • Docker

  • Git

  • Linux

  • AWS

  • MySQL

  • Pandas

  • Github

  • Scikit-learn

  • Numpy

Workflow
  • ETL/ELT Pipeline Design and Implementation
  • Collaboration with Cross-Functional Teams
  • Data Cleaning and Preprocessing
  • Data Visualization
  • Performance Optimization in Big Data Environments

Certifications and Courses

Badges