Data Scientist at Metegrity Inc. | Machine Learning Pipelines & Production Analytics

About

Data Scientist focused on building end-to-end machine learning systems that turn messy, real-world data into reliable production solutions. My work spans the full lifecycle, from data pipeline development and feature engineering to model training, optimization, and production deployment. I put a strong emphasis on automation, monitoring, and long-term maintainability.

I design pipelines that handle the unglamorous but critical parts of ML. That means cleaning inconsistent data, automating feature selection, training and evaluating multiple model variants, and selecting the best performer based on business-relevant criteria. Beyond model development, I build the infrastructure around it. Structured logging, data validation, drift detection, and scheduling so that systems run reliably without constant manual oversight.

I work closely with cross-functional teams to replace manual, time-intensive processes with scalable, data-driven workflows. I also take ownership of production readiness by assessing gaps across areas like data versioning, experiment tracking, and CI/CD, and putting together roadmaps to close them over time.

I’m always looking to learn and improve, whether that means refactoring a codebase to cut complexity, picking up better tooling, or rethinking an approach that isn’t working. At the end of the day, I care about building things that are not just accurate but maintainable, auditable, and genuinely useful to the people who rely on them.

Current Role

• Design and maintain end-to-end machine learning pipelines, from data ingestion and feature engineering through model training and production deployment.
• Build monitoring and validation systems to ensure model reliability over time.
• Work with cross-functional teams to integrate predictive analytics into operational workflows, replacing manual processes with data-driven decision-making.
• Conduct production readiness assessments and develop roadmaps for scaling ML systems.
• Refactor and optimize analytical codebases to reduce complexity and improve maintainability.

Skills

XGBoost

MLOps

R Programming

Feature Engineering

Data Pipeline Development

Project Portfolio

1. Scraping and Analyzing Steam Game Reviews
   • Skills: Web-Scraping, Data Cleaning, EDA, Statistical Testing, Sentiment Analysis, Data Visualization, Predictive Modeling
   • Tools: Python (Pandas, NumPy, Matplotlib, Scikit-learn, Beautiful Soup, Selenium), SQL, Tableau, Git
2. Building Machine Learning Algorithms for Predicting COVID-19
   • Skills: Data Preprocessing, EDA, Predictive Modeling, Feature Importance Evaluation, Statistical Analysis, ML Algorithm Tuning
   • Tools: R (dplyr, ggplot2, caret), Python (Pandas, Scikit-learn), Algorithms (Logistic Regression, KNN, Decision Trees, Random Forest, SVM, XGBoost)