-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Jorge Gomez
committed
Apr 25, 2024
1 parent
5853762
commit e10b248
Showing
17 changed files
with
107 additions
and
57 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,29 @@ | ||
--- | ||
layout: milestone | ||
title: Walmart Global Tech | ||
description: Machine Learning Engineer | ||
date-start: 2022-01-13 | ||
date-end: Present | ||
img: /img/walmart.jpg | ||
--- | ||
|
||
I joined <a href="https://tech.walmart.com/content/walmart-global-tech/en_us.html" | ||
target="_blank">Walmart Global Tech</a> in 2022 to work on Neural Machine Translation. My | ||
contributions encompass all fronts of the Data Science lifecyle: data engineering, ML modeling and | ||
evaluation, MLOps, and deployment. This has helped me develop an end-to-end mindset when building ML | ||
solutions. | ||
|
||
I have been involved in two projects: Query Translation and Item Translation – both of them already | ||
deployed in production. The first one aims to enable search for Spanish-speakers at <a | ||
href="https://www.walmart.com" target="_blank">walmart.com</a>. By means of Language Detection and | ||
Machine Translation, we map Spanish queries to their English equivalent to allow the downstream | ||
systems to work transparently. A paper describing our solution is available <a | ||
href="https://dl.acm.org/doi/abs/10.1145/3543873.3587660" target="_blank">here</a>. | ||
|
||
On the other hand, Item Translation is focused on translating the catalog of one market to one or | ||
many target languages. We trained custom translation models and leveraged several services in the | ||
Google Cloud Platform to translate to French more than 100M items indexed at <a | ||
href="https://www.walmart.ca/fr" target="_blank">walmart.ca</a>. Currently, we are on the way to | ||
translate the content of <a href="https://www.walmart.com" target="_blank">walmart.com</a> to Spanish. | ||
|
||
We continue to scale these solutions to handle more translation use cases within the company. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,21 +1,20 @@ | ||
--- | ||
layout: milestone | ||
title: 3Pillar Global | ||
title: Egnite Health | ||
description: Data Scientist | ||
date-start: 2020-06-06 | ||
date-end: Present | ||
date-end: 2021-12-31 | ||
img: /img/3pillar.png | ||
--- | ||
|
||
<a href="https://www.3pillarglobal.com" target="_blank">3Pillar Global</a> (formerly <a href="https://www.tiempodev.com">Tiempo Development</a> in Mexico) is a consultancy company with several clients around the world. My role here is in two different fronts: working with a specific client and building 3Pillar's offering portfolio in Data Science. | ||
In a span of one year and a half, I worked at <a href="https://egnitehealth.com" target="_blank"> | ||
Egnite Health</a> researching and applying Computer Vision models to automate the detection of heart | ||
diseases. Such models were developed in TensorFlow from scratch and trained on Databricks. We | ||
explored traditional Convolutional Neural Networks as well as multi-instance learning. | ||
|
||
The specific client I work with is <a href="https://egnitehealth.com" target="_blank">Egnite Health</a>. Here, my role is that of an ML Engineer. I research state-of-the-art models in Computer Vision to solve several problems related to heart diseases. In the engineering side, I have developed internal libraries for data wrangling, model training, and other utility functions for the pipeline. Several models have been implemente from scratch with TensorFlow and are tracked with MLFlow. | ||
In addition to the ML modeling, I developed internal libraries for data wrangling that were | ||
HIPAA-compliant. This was critical to ensure the privacy of the patients during model training and | ||
evaluation. I also developed internal tools that helped domain-experts to evaluate the performance | ||
of our models. | ||
|
||
With respect to the offering portfolio, I work directly with 3Pillar's Head of Data Science. My job is to create an internal portfolio of projects and infrastructure. This includes proposal of internal projects, client engement, mentoring of Jr. Data Scientists, and Data Science education across the whole company. | ||
|
||
<!-- <div class="img_row"> | ||
<img class="col three" src="{{ site.baseurl }}/img/pic-tue-thesis.jpg" alt="" title="Thesis defense at TU/e"/> | ||
</div> | ||
<div class="col three caption"> | ||
Thesis defense at the TU/e campus. From left to right: dr. George Fletcher, dr. Decebal Mocanu, dr. Joaquin Vanschoren, and I. | ||
</div> --> | ||
Some other contributions were survival analyses on tabular data to model the risk of heart disseases. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Oops, something went wrong.