Santiago is available for hire

Santiago Miguel Vélez Castañeda

Verified Expert in Engineering

NLP Developer

Location

Medellín - Antioquia, Colombia

Toptal Member Since

February 28, 2022

Santiago is a data scientist with over five years of experience in the IT industry. He focuses on deep learning sequential models, machine learning, Python data science stack, and cloud ML and AI. Santiago enjoys solving complex problems and hard questions using data science, which allows him to model different events and translate the results into real-world solutions.

Machine Learning Deep Learning Python PyTorch NumPy R Git Bash TensorFlow Keras SQL AIOps

Portfolio

Microsoft

Python, Data Science, Machine Learning, Deep Learning, Azure

Globant

Python, PyTorch, Machine Learning, Deep Learning, Data Science

iDATA

Python, Data Science, Machine Learning, Deep Learning

Experience

Data Science - 5 years Machine Learning - 5 years Python - 5 years PyTorch - 4 years Deep Learning - 4 years NumPy - 4 years Azure - 4 years R - 2 years

Availability

Part-time

Preferred Environment

PyTorch, Python, R, NumPy, Data Science, Machine Learning, Deep Learning, Azure

The most amazing...

...thing I've developed is a transformer-based model to create documentation from code snippets.

Work Experience

Cloud Solution Architect for Data and AI

2020 - 2021

Microsoft

Detected near real-time frauds in telecom company with PyTorch and AKS.
Contributed to the in-call speech-to-text transcription with Azure Speech and Python.
Provided technical guidance for the Catalyst project time crunching 5G RAN rollout with AI.

Technologies: Python, Data Science, Machine Learning, Deep Learning, Azure

Senior Data Scientist

2019 - 2020

Globant

Created the software development-oriented ML models for the augmented coding website.
Conducted the automatic sequence summarization with transformer architecture in PyTorch.
Developed search engines by applying recurrent neural networks, language models, and fully connected networks.

Technologies: Python, PyTorch, Machine Learning, Deep Learning, Data Science

Data Scientist

2017 - 2019

iDATA

Played a key role in time series forecasting with LSTM recurrent neural network using Keras, TensorFlow, and GPU computing.
Led a team of four data scientists for an anomaly detection project with nationwide impact within a government agency.
Managed the operationalization in a public cloud of three data science developments within the Colombian oil and gas company.

Technologies: Python, Data Science, Machine Learning, Deep Learning

Experience

Deep Learning Models for Software Development

Augmented Coding is a set of tools that leverage the power of AI to enhance the coding process, making it easier for developers to cover compliance needs over documentation, reuse of existing code, and code retrieval within the IDE.

I helped create deep learning models to enable semantic code search and automatic code documentation.

Imports Fraud Detection for Government Agency

I led a data science team to develop a machine learning system that detected anomalies in imports information for one of Colombia's leading government agencies. The project was developed using open-source software and cloud architectures.

Customer Experience Analysis and Churn Prediction Using Call Recordings

I designed the architecture and helped the partner team develop a machine learning solution to analyze semantic and audio features from calls, evaluate customer experience, and predict churn. The project was developed and deployed on Azure.

Education

2021 - 2022

Master's Degree in Computer Science

Universite de Montreal - Montreal, Canada

2019 - 2020

Specialization in Analytics

Universidad Nacional de Colombia - Medellin, Columbia

2013 - 2017

Bachelor's Degree in Marketing

Universidad de Medellin - Medellin, Columbia

Certifications

FEBRUARY 2021 - FEBRUARY 2023

Azure Data Scientist Associate

Microsoft

MAY 2020 - MAY 2022

Azure AI Engineer Associate

Microsoft

MAY 2020 - PRESENT

Deep Learning Specialization

Coursera

Skills

Libraries/APIs

PyTorch, NumPy, TensorFlow, Keras

Tools

Git

Languages

Python, R, Bash, SQL

Paradigms

Data Science

Platforms

Azure

Other

Deep Learning, Machine Learning, AIOps, Cloud

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring