Catalina Urdaneta Bernal

Expertise Overview

Senior Data Scientist & Automation Engineer with 9+ years of experience building and operating production-grade data systems.

I design and implement end-to-end pipelines that automate data acquisition, large-scale web scraping, enrichment workflows, and machine learning systems used in real business environments.

With a background in Electronic Engineering and deep expertise in Python, SQL, cloud platforms, and LLM-based agents, I focus on solving complex, unstructured data problems where reliability, scale, and automation actually matter.

9+

Years Experience

40%

Workflow Efficiency Improvement

100+

Projects Delivered

Technical Expertise

AI SYSTEMS & ARCHITECTURE

LLM-powered agents (RAG, tool calling, orchestration)
Multi-source data ingestion & enrichment pipelines
Vector databases & semantic search
Production-ready AI workflows

DATA ACQUISITION & WEB INTELLIGENCE

Large-scale web scraping & crawling
Anti-bot strategies & resilient scrapers
Data normalization & entity resolution
Email & contact enrichment pipelines

AUTOMATION & DATA OPS

ETL Pipelines
Workflow orchestration (Airflow)
Data validation & monitoring
Fail-safe & recovery strategies
Scalable & maintainable infrastructure

Programming

Python, JavaScript
SQL, Dash, Flask
FastAPI, LangChain

Data Science & AI

Machine Learning, Deep Learning
TensorFlow, Scikit-learn
NLP, RAGs, LLM Agents

Cloud & Tech

AWS, PostgreSQL
Power BI, Domo
Git, CI/CD, Linux

How I apply AI in real systems

Automating data extraction, classification, and enrichment
Building LLM agents connected to live data sources
Reducing manual operations through AI-driven workflows
Designing systems where AI decisions are traceable and reliable

Professional Journey

Data Operations Manager

vLex International · 09/2023 – 10/2025

Built Python scraping + enrichment pipelines for global legal/business data.
Developed LLM agents + RAG + custom search engines for classification & retrieval.
+30% sync speed · +20% data accuracy · -40% manual workload.

Data Science Manager

Schlumberger · 10/2021 – 06/2023

Designed and deployed ML systems (prediction/classification/clustering) with end-to-end MLOps workflows in Python.
Delivered a 40% application load-time reduction through optimization, caching, and modular architecture.
Awarded Global Innovation Award (2nd place) for “History Matching Optimization”.

RPA/RDA Developer

Tata Group · 01/2020 – 10/2021

Built end-to-end RPA solutions with Pega Robotics for banking operations; standardized workflows and mentored developers.
Created a reusable GitHub code library, cutting development time by 25% and reducing QA cycles by 30% with improved testing/deployment.
Maintained 90%+ code quality and zero critical production defects.

Senior Business Analyst

Global Hits / Claro Colombia · 04/2019 – 12/2019

Analyzed large-scale network/customer data (Python/R/Linux) and built internal automation tools in JavaScript for QA and monitoring.
Managed Oracle databases and ETL pipelines for reporting integrity.

Developer Engineer

Ascendi · 08/2018 – 01/2019

Developed and programmed microcontroller systems (PSBs and ADMs) for crane control.
Optimized automation reliability and operational safety in construction.

Full-time Professor

INCCA University · 08/2018 – 01/2019

Taught Computational Intelligence, Databases, and OOP courses.
Mentored engineering students and led applied research projects in systems design.

Technical Support Engineer

Medetech SAS · 08/2017 – 08/2018

Provided technical support and training for Philips/Sonoscape medical equipment.
Conducted research on telemedicine systems and translated technical documentation.

Projects Assistant Engineer

Proindustrial de Básculas SAS · 09/2014 – 05/2017

Planned and supervised production/assembly of industrial weighing systems.
Ensured calibration accuracy and operational efficiency across installations.

Technical Software Operator

Xion Automatización · 01/2014 – 06/2014

Maintained and developed PLC-based industrial control software.
Implemented API modules for machine interfaces and performed electronic diagnostics.

Full Stack Developer

Digitax · 02/2013 – 12/2013

Developed Android and iOS mobile applications in Java and C#.
Optimized app performance and ensured backend integration via JSON/Databases.

Data Scientist & Automation Engineer