| | | 20,000+ Fresh Resumes Monthly | |
|
|
| |
Click here or scroll down to respond to this candidateCandidate's Name
Expert Machine Learning Engineer | Senior Data Scientist | AI & ML
Specialist
Address Texas City, TX, Street Address United States
Phone PHONE NUMBER AVAILABLE
E-mail EMAIL AVAILABLE
With a decade of experience in Machine Learning, I offer deep expertise in Python, R, and Java. My
skills encompass advanced algorithm development, data preprocessing, feature engineering, and
model evaluation. I have worked across various domains, including computer vision, natural
language processing, and recommender systems. Proficient in deploying models with Docker,
Kubernetes, and AWS, I bring hands-on experience in production environments. My expertise
extends to TensorFlow and PyTorch, where I leverage deep learning architectures to enhance
model performance. I am skilled in SQL for effective data manipulation and have a solid grasp of
distributed computing frameworks like Apache Spark. My achievements include developing NLP
systems that significantly improved customer satisfaction and employing graph-based algorithms to
enhance recommendation system diversity. My focus is on implementing scalable, efficient
machine learning pipelines to deliver impactful solutions.
Skills
Programming Skills: Proficient in Python and R, with expertise in TensorFlow and Keras.
Deep Learning: Deep knowledge in Convolutional Neural Networks (CNNs), Long Short-
Term Memory networks (LSTMs), and Natural Language Processing (NLP).
Project Leadership: Led diverse projects that enhanced user experiences with advanced AI
solutions across various industries.
Big Data Tools: Experienced with big data technologies such as Spark, Hadoop, and Kafka.
Cloud Platforms: Skilled in deploying scalable solutions using AWS, GCP, and Azure.
Machine Learning Libraries: Proficient in ML libraries like PyTorch and scikit-learn.
Visualization: Expertise in using visualization tools to apply cutting-edge techniques for real-
world innovation.
Work History
May 2019 - Principal Data Scientist
Current Guild Education
Sales Forecasting:
- Implemented time series forecasting for inventory management using R,
Prophet, and Spark.
- Collected historical sales data, inventory levels, and promotional activity.
- Cleaned and preprocessed data using R, addressing missing values and
seasonality.
- Developed features such as sales trends, seasonality factors, and
promotional impacts.
- Implemented Prophet for time series forecasting, leveraging Spark for large-
scale data processing.
- Evaluated models using Mean Absolute Error (MAE) and Root Mean Squared
Error (RMSE).
- Deployed the forecasting model on AWS, integrating with the inventory
management system.
Outcome: Optimized inventory levels, reducing costs by 20%.
Recommendation Engine:
- Built a recommendation engine for personalized shopping experiences using
Python, Scikit-learn, and AWS.
- Collected customer transaction data, product details, and browsing
behavior.
- Cleaned and normalized data using Python and Pandas.
- Developed features such as user preferences, purchase history, and product
similarity.
- Implemented collaborative filtering algorithms using Scikit-learn to generate
recommendations.
- Assessed model performance using precision, recall, and F1-score.
- Deployed the recommendation engine on AWS, providing real-time
personalized suggestions.
Outcome: Increased customer engagement by 25%.
Leadership and Analytics:
- Managed a team of 6 data scientists, providing mentorship and technical
guidance.
- Worked closely with business leaders to understand their needs and develop
data-driven solutions.
- Oversaw project timelines, deliverables, and ensured alignment with business
objectives.
Mar 2015 - Lead Data Scientist
May 2019 Everlane
Predictive Healthcare Analytics:
- Built predictive models for patient readmission rates using Python, Keras, and
AWS.
- Collected patient data from electronic health records (EHRs) including
medical history, treatments, and outcomes.
- Cleaned and preprocessed data using Python, handling missing values and
normalizing features.
- Created features such as treatment efficacy, patient demographics, and
historical readmission patterns.
- Developed deep learning models using Keras to predict readmission risk.
- Evaluated models using metrics such as accuracy, precision, recall, and
ROC-AUC.
- Deployed models on AWS, integrating them with the hospital's patient
management system.
Outcome: Decreased readmission rates by 15%.
Medical Image Analysis:
- Developed image classification models for disease diagnosis using
TensorFlow, OpenCV, and Azure.
- Collected medical images including X-rays, MRIs, and CT scans.
- Preprocessed images using OpenCV, including resizing, normalization, and
augmentation.
- Utilized convolutional neural networks (CNNs) to extract features from
images.
- Implemented TensorFlow to develop deep learning models for image
classification.
- Evaluated models using metrics such as accuracy, precision, recall, and F1-
score.
- Deployed models on Azure, integrating them with the hospital's diagnostic
system.
Outcome: Improved diagnostic accuracy by 25%.
Collaboration and Reporting:
- Collaborated with doctors and medical staff to identify key areas for
improvement.
- Developed data-driven solutions to address clinical challenges and improve
patient outcomes.
- Prepared detailed reports and presentations for medical stakeholders.
Feb 2011 - Senior Data Scientist
Mar 2015 Quaid Ventures
Customer Segmentation:
- Implemented customer segmentation using clustering techniques with
Python, Scikit-learn, and Pandas.
- Collected customer transaction data, demographic information, and
behavioral data.
- Cleaned and normalized data using Python and Pandas.
- Developed features such as purchasing frequency, average transaction
value, and customer lifetime value.
- Implemented clustering algorithms using Scikit-learn to segment customers.
- Assessed model performance using silhouette score and within-cluster sum of
squares (WCSS).
- Integrated customer segmentation insights into the CRM system.
Outcome: Improved targeted marketing efforts, resulting in a 20% increase in
sales.
Fraud Detection System:
- Developed a fraud detection model for financial transactions using R,
TensorFlow, and SQL.
- Collected transaction data, user behavior patterns, and fraud reports.
- Cleaned and normalized data using R, handling missing values and scaling
features.
- Developed features such as transaction frequency, amount patterns, and
user profiles.
- Implemented deep learning models using TensorFlow for anomaly detection.
- Assessed model performance using True Positive Rate (TPR) and False
Positive Rate (FPR).
- Deployed models into the financial system for real-time fraud detection.
Outcome: Reduced fraudulent transactions by 30%.
Team Collaboration:
- Worked with IT, finance, and marketing teams to understand business needs.
- Developed and deployed machine learning models into existing systems.
- Prepared detailed reports and presentations for senior management.
Education
Bachelor of Science: Computer Sciences
Rice University
|
