Experience
A chronological selector of my software engineering and data science career.
Data Analyst @ ASUITECH Solutions
SQL
Python
Power BI
Tableau
Snowflake
MySQL
AWS Lambda
MongoDB
PowerShell
- Developed interactive business intelligence dashboards and operational visual reports using Power BI and Tableau.
- Wrote, tuned, and optimized SQL queries to query Snowflake databases, boosting report retrieval times.
- Collaborated closely with cross-functional business stakeholders to translate specifications into visual metrics.
- Identified key data anomalies, patterns, and trends, supplying reports to support executive planning.
- Automated operational report compilation and ingestion workflows utilizing Python and PowerShell scripting.
- Created strict validation rules to guarantee data format accuracy and consistency.
Software Developer @ DATA Bricks
Java
Python
SQL
Spring Boot
Hibernate
Junit
Git/GitHub
Jira
Agile
CI/CD
- Wrote, tested, and shipped clean backend code using Java, Spring Boot, and SQL databases.
- Diagnosed, troubleshot, and patched complex application and environment bugs to maintain high availability.
- Managed code deployments and version control branches inside Git/GitHub environments.
- Produced thorough unit testing logic using JUnit to ensure stability prior to branch merge.
- Participated actively in daily Scrum stand-ups, code reviews, and Agile project tracking via Jira.
- Authored clear system design documents, setup guides, and REST API endpoints specifications.
Research Assistant @ University of Memphis
Python
Pandas/NumPy
Scikit-learn
TensorFlow
Apache Spark
Docker
AWS EC2/S3
MATLAB
SciPy
- Engineered and trained predictive ML models on large-scale datasets (up to 500GB) using Python (Pandas, Scikit-learn).
- Pioneered extensive feature engineering and data validation pipelines, boosting model AUC scores by 15%.
- Spun up, monitored, and optimized AWS EC2 compute instances and S3 storage configurations.
- Architected Deep Learning models (TensorFlow/Keras) for complex time-series anomaly detection, achieving 92%+ accuracy.
- Processed big data pipelines utilizing Apache Spark (PySpark) across distributed clusters.
- Containerized ML environments with Docker, ensuring reproducible deployments from local hosts to cloud endpoints.
- Conducted statistical significance analysis and hypothesis testing using SciPy.