Data Engineer, External Workforce at Google:- Spearheaded the integration of diverse healthtech data sources on Google Cloud, optimizing data flow. Improved clinical decision support systems for enhanced patient care.- Engineered advanced data solutions on Google Cloud, boosting system performance. Accelerated medical research and analysis for personalized healthcare approaches.- Pioneered innovative data solutions, leveraging Google Cloud for improved data quality and accessibility. Facilitated insights to streamline healthcare operations and enhance patient outcomes.

Data Engineer

- Develop, Train, Deploy and Continuously Trained NLP models for spam detection. Accelerating 10x the moderation process on millions of messages on a daily basis.- Develop automated ETL process to unstructured data for retraining ML models. In order to continuously train, and control the often evolving spam messages problem.

Machine Learning Engineer

<ul><li>Implemented Deep Learning computer vision algorithms for granulometry at a big scale applied to coffee trading companies.</li><li>Implemented Machine Learning models for detection of humidity, classification, and comparison of quality applied to NIRS technology readings of Coffee.</li></ul>Tech-Stack: Python, Torch, Keras, Tensorflow, OpenCV, Numpy, GIT, Github, GCP, Jira, Airflow.

Data Scientist

<ul><li>Responsible for developing cloud-based solutions in GCP using Python for a health monitoring service based on IOT devices, giving the company data for analysis and a competitive advantage to offer as a service.</li><li>Develop Big Data ETLs deploying them on a GCP cloud and DataBricks.</li><li>Used Spark for data decompression and high-performance conversion.</li></ul>Tech-Stack: Python, Spark, PySpark, DataBricks, Numpy, GIT, Bitbucket, GCP, Sonarcloud, Jira.

<ul><li>Design and implement a commercial leads solution for the company that increased the success rate of the sales department by more than 300% and scoped the sales efforts hot leads by providing +2000 leads monthly that previously had to be gathered manually at a rate of 5 per day.</li><li>Develop NLP models and automate data pipelines for big data on AWS infrastructure.</li></ul>Tech-Stack: Python, Pandas, Numpy, GIT, Spacy, tensorflow, API rest, GCP, AWS, Docker.

<ul><li>Worked with Django framework for maintaining a codebase while synchronizing with the business area to improve customer experience. </li><li>Optimize processes for data transformations and data migrations for customer database migrations for new company clients.</li></ul>Tech-Stack: Python, Pandas, Django, GIT, CircleCI.

Python Backend Developer

<ul><li>Developed a solution for the AMVA (Metropolitan Area of the Aburrá Valley) by migrating from manual work on several spreadsheets to a web application using Python, Flask, Telegram API, and automated tasks on windows servers on cloud infrastructure saving +200 hours per month in operational tasks, delivery time of reports was reduced to almost real time, and errors in manual entry were reduced by 99%.</li><li>Participated in the migration and implementation team of the DataBase and reporting system for the public transportation control for the city (Medellin and AMVA). A big data solution that allowed to register real time data from all the public transportation in the city and measure indicators that allowed to know a close approximation of the passenger flow in the city providing insights for making decisions that included the measure of the impact during Covid crisis times. </li></ul>Tech-Stack: Python, Pandas, Numpy, Flask, Oracle RDBMS, GI

Senior Data Analyst

<ul><li>Developed NLP pipeline for employee satisfaction surveys and presented the final result to the board to be included as part of the core services provided by the company. With this, the experience of the final client improved as it allowed them to see detailed information from all departments inside the company saving hundreds of hours reviewing surveys.</li></ul>Tech-Stack: Python, Pandas, Numpy, GIT, Tensorflow, Scikit Learn, Snowflake, GCP.

Senior Data Scientist

<ul><li>Developed a Computer Vision microservice for automating the edition of Graphic assets in order to generate catalogs in a faster way for a clothing brand. The microservice was entirely written in python and used a Hadoop DFS to store and load the RAW images from the servers. Accuracy was 80% better than the previous version implemented. </li><li>Lead a team to develop a solution to forecast and optimize RPA licensing. Final project costs were reduced by 20%. </li></ul>Tech-Stack: Python, Pandas, Numpy, Azure, Oracle RDBMS, GIT, HadoopDFS

<ul><li>Developed and deployed microservices to find fraud, and recommendation systems as a part of the growth team in the company. </li><li>All these products were developed in a really fast-paced environment with Quality and Punctuality. </li></ul>Tech-Stack: Python, Pandas, Numpy, Tensorflow, PostgreSQL, MongoDB, Snowflake, GIT.

<ul><li>Developed the ML core of “black box” a flexible recommendation system for content online.</li><li>Developed core for MVP prototypes for selling to company clients and prospects.</li></ul>Tech-Stack: Python, Pandas, Numpy, IBM Watson, MySQL, GIT, Tensorflow.

Personal details

Julian A.

Summary

Technical skills

Work Experience

Education