I am a professional passionate about the intersection between engineering and data science. Currently, I am pursuing a Master’s Degree in Data Science at the Universidad de Sonora, focusing on Natural Language Processing (NLP) and the development of Large Language Models (LLMs).
My experience combines the analytical foundation of chemical engineering with modern software development and data analysis tools.
Education
Master’s Degree in Data Science | Universidad de Sonora
August 2023 - June 2026
Focus on Python, SQL, NoSQL databases, ETL processes, machine learning models, neural networks, NLP, and time series analysis.
Bachelor’s Degree in Chemical Engineering | Universidad de Sonora
August 2018 - June 2023
Skills in process simulation and optimization (MATLAB, ASPEN HYSYS).
Professional Experience
Data Scientist | CT Internacional
February 2025 - Present
Engineered and deployed a production-grade multi-agent chatbot with LangGraph and Vertex AI (Gemini), migrating from LangChain/OpenAI, with a multi-tool RAG pipeline over structured and semi-structured data (SQL, XML, PDF) for product search, promotions, and warranty queries. Built an LLM-as-judge monitoring stack and a GitHub Actions + Podman CI/CD pipeline for reproducible deployments. Also built and deployed Pulse, a customer analytics platform automating RFM/K-Means segmentation and FP-Growth market basket analysis behind a FastAPI + DuckDB + Plotly dashboard, running self-supervised on an on-premise server.
Data Scientist | DARIG – Consultores (Salsas Castillo)
March 2025 - Feb 2026
Developed GlorIA, an internal AI assistant with OpenAI function-calling and SQL toolkits to automate executive reporting, integrated with Telegram for on-the-go KPI queries. Led the architectural transition from a RAG prototype to a Model Context Protocol (MCP) framework, enabling autonomous SQL execution and improving long-term maintainability.
Data Engineer | DARIG – Consultores (Frutal)
October 2025 - Feb 2026
Resolved critical Stack Smashing memory errors caused by unstable legacy ODBC drivers by designing a containerized (Podman) cross-platform ETL pipeline, migrating 6 production tables from a legacy HFSQL database to Parquet format on Google Cloud Platform for executive dashboards.
Data Scientist | National Energy Control Center (CENACE)
May 2024 - Feb 2026
Designed a secure, on-premise RAG system (FastAPI, Ollama, FAISS) to optimize the IT help desk’s incident resolution across 2,800 historical tickets, achieving a 24.4-second average response time and a 4.4/5 technical precision rating. Built an automated feedback loop to re-ingest high-rated responses and an ML-based ticket classification system to streamline triage.
Technical Skills
Languages
Python SQL NoSQL JavaScript
AI & Data Science
LangChain LangGraph Vertex AI / Gemini Ollama Hugging Face Scikit-learn Pandas NumPy Matplotlib Seaborn RAG MCP
Databases
PostgreSQL MySQL MongoDB FAISS Redis HFSQL DuckDB
Development & DevOps
FastAPI Docker/Podman Git/GitHub DagsHub GCP Plotly
Certifications
Data Analysis – DataCamp ML Scientist in Python – DataCamp Data Science with Python – DataCamp
Languages
🇲🇽 Spanish — Native
🇺🇸 English — Fluent
🇵🇹 Portuguese — Fluent
🇫🇷 French — Fluent
🇯🇵 Japanese — Intermediate
🇩🇪 German — Intermediate
Interests
I am passionate about continuous learning of languages and cultures — I currently speak 6 languages. I enjoy dancing and traveling, and I am deeply motivated by applying technology to solve real business problems through data and artificial intelligence.
