Luis Robles Guerrero
Data Scientist / Machine Learning Engineer
Phone: 281-***-**** Email: adr2we@r.postjobfree.com
Professional Summary
6+ years of experience working in Data Science and Machine Learning field.
Extensive experience in applying data preprocessing, statistical analysis, data analytics tools, predictive modelling, model deployment and evidence-based approaches to find lean, actionable solutions to various real-world enterprise business problems.
Experience in the application of Supervised and Unsupervised Learning algorithms, Naïve Bayes, Regression Analysis, Neural Networks/Deep Learning, Support Vector Machines (SVM), Random Forest, K-Means, Hierarchical, Spectral clustering, DBSCAN, Collaborative Filtering and other advanced machine learning techniques.
Used AWS Cloud Services Sagemaker, ECS, EKS, S3, Redshift, QuickSight
Experience with Google Cloud Platform (GCP) AutoML, Vertex AI, BigQuery, Colab, DataProc, Data Studio,
Exposure to Azure ML, PowerBI, Azure SQL and DataBricks
Design custom BI reporting dashboards or interactive data visualizations and widgets in R and Python using Shiny, Tableau, Ggplot2, Plotly, Matplotlib, and Seaborn.
Produce custom BI reporting dashboards in R and Python using Shiny, and Plotly for rapid dissemination of actionable, data driven insights.
Strong experience in Software Development Life Cycle (SDLC), MLOPS, and in supervising internationally distributed teams of domain specific experts to meet product specifications and benchmarks within the deadlines given.
Experience in working with relational databases (Teradata, Oracle) with advanced SQL skills.
Skills
Machine Learning & Deep Learning:
●K-Nearest Neighbors (KNN)
●K-means clustering
●Random forests
●Decision trees
●Linear regression
●Logistic regression
●Polynomial regression
●Multivariate regression
●XGBoost
●Reinforcement Learning
●Artificial Neural Network (ANN)
●Convolutional Neural Network (CNN)
●Recurrent Neural Network (RNN)
●LSTM
●Transfer Learning
●Auto encoding/decoding
●Feature Engineering
●Model Validation
Libraries/Tools:
●Numpy
●TensorFlow Hub
●Scipy
●TensorFlow Serving
●Sympy
●Pandas
●PyTorch
●Keras
●Sklearn
●Skimage
●Selenium
●Matplotlib
●Plotly
●Seaborn
●Ggplot2
●Unittest
●PyTest,
●PySpark
●OS and Keras with a TensorFlow backend
●Flask
●KuberFlow, CodePipeline
Management:
●Experience managing small inter-disciplinary teams consisting of data scientists and subject matter experts in the project domain
●Able to prioritize tasks to reach project goals
●Time Management
●Scrum oriented
Programming Languages:
●Python
●Object-oriented programming (C++)
●R
●MATLAB
Databases:
●SQL Server
●PostgreSQL
●Oracle
●NoSQL
Communication:
●Excellent listener
●Able to convey complex ideas to both technical team members and non-technical stakeholders
Cloud Environments:
●Amazon Web Services (AWS)
●Google Cloud Platform (GCP)
●Azure
Big Data Stack:
●Hadoop Data Lake
●Snowflake
●Spark
Theory:
●Linear Algebra Math
●Optimization Theory
●Object Oriented Programming
●Data Structures and Algorithms
Professional Experience
Data Scientist & Machine Learning Engineer 09/2020 - Present
San Antonio ISD San Antonio
I led a team of machine learning experts, data engineers and data scientists to create and test a computer vision solution for detecting weapons on school grounds using internal security camera footage. Implemented several pretrained and custom fine-tuned convolutional neural networks and deployed them on the cloud (AWS)
●Developed a custom dataset for fine-tuning a deep neural network.
●Fine-tuned a variety of image models with object detection heads.
●Created end to end, from data wrangling, coding and deployment for all the models
●Used both Single Shot Detection (SSD) and You Only Look Once (YOLO) object detection models.
●MLOPs: Used AWS Sagemaker involving ECS, EKS, Redshift, S3, Quicksight, CodeBuild and CodePipeline – a CI/CD Pipeline in AWS for Model deployment
●Deployed finished model on edge devices using Tensorflow-Lite.
●Used pre-trained models to visualize the feature maps in the intermediate layers and performed transfer learning
●Used pre-trained models (VGG16, ResNets, Inceptions, DenseNet, U-Net, etc.) for transfer learning on small datasets
●Lead various cross-department projects and worked closely with internal stakeholders such as business teams, product managers, engineering teams
Data Scientist 10/2018 - 09/2020
Credit Suisse New York City, New York
I developed a model ensemble to predict “meme” stocks occurrence and performance. The model was a combination of NLP and Time Series Analysis. We tracked a series of stocks and created an NLP algorithm to establish a buy, hold or sell score for each tracked security based on social media mentions. Once a daily score was calculated we used time series analysis to generate a series of forecasts. Used Google Cloud Platform machine learning and storage services for deployment.
●Implemented application of various machine learning algorithms and statistical modeling like Decision Trees, Text Analytics, NLP, Sentiment Analysis, Naive Bayes, Logistic Regression and Linear Regression using Python and determined performance.
●Interpreted analytical results to resolve algorithmic success, robustness and validity
●Implemented both Elmo and BERT embeddings to correctly encode text.
●Used a variety of NLP methods for information extraction, topic modeling, parsing, and relationship extraction.
●Used GCP AutoML, VertexAI, Colab, DataProc and BigQuery services
●Deployed models on GCP Container and Kubernetes Engines
●Implemented Agile Methodology for building an internal application
●Implemented MLOPS CI/CD pipelines using Kuberflow, CloudBuild
●Wrote a Flask app to call CoreNLP for parts-of-speech and named entity recognition on natural English queries.
●Optimized SQL queries to improve performance of data collection.
●Design, develop and produce reports that connect quantitative data to insights that drive and change business
Junior Data Scientist / 07 2016 to 10 2018
CEMEX Zurich, Switzerland / Houston. Texas (Remote)
I was a part of a data science team on a multinational project for CEMEX where we worked on building prediction models of mechanical properties of compounds and materials
●Defined project benchmarks on data mining, processing, and storage, to create clean and usable data sets from raw data.
●Established the machine learning model used for mechanical properties prediction.
●Created a preliminary app integrating the prior developed prediction model and cost optimizations algorithms using Python machine learning libraries.
●Design, develop and produce reports that connect quantitative data to business insights
●Outcomes from projects mentioned above led to application of these technologies in other areas such as supply chain, logistics and finance.
●Coordinated with an international and multicultural team to successfully execute multiple projects within the machine and deep learning space
Education
ITESM (Tecnológico de Monterrey, Monterrey, Mexico) – Bachelor of Science in Engineering Physics
●Specialization in Deep Learning & Quantum Computing
Certifications
Machine Learning Specialization in Amazon Web Services (In Progress)
●Building, training, tuning, and deploying machine learning (ML) models on AWS, MLOPS.