Clemson University Graduate • MS Computer Science

Data Intelligence Engineer

I build end-to-end analytics solutions—from ETL pipelines and data warehouses to ML models and executive dashboards—specializing in healthcare analytics and product intelligence.

3.87 GPA @ Clemson
368K+ Records Analyzed
0.84 F1 Score (NLP)
Download Resume View Projects

What I Bring to Your Team

Python SQL Apache Spark dbt Power BI AWS Machine Learning Tableau
ROC-AUC 0.79 Clinical Risk Model
96.3% Data Quality Score
60% Processing Time Reduction
85% Forecast Accuracy

Featured Projects

Production-ready analytics solutions demonstrating my ability to deliver measurable business impact through data

Healthcare Analytics

CardioInsight-AI

Python dbt Power BI ML

End-to-end clinical risk analytics platform transforming 68K+ patient records into actionable cardiovascular insights for healthcare providers

68K+ Patient Records
0.79 ROC-AUC
96.3% Data Quality
  • Built HIPAA-compliant ETL pipeline with dbt-engineered star schema and 20+ data quality checks
  • Developed logistic regression and tree-based models achieving 0.79 ROC-AUC for cardiovascular risk prediction
  • Designed interactive Power BI dashboards with patient-level drilldown enabling clinical decision support
  • Engineered 15+ clinical features including risk stratification and demographic-clinical interactions
Live Dashboard GitHub
Product Analytics • NLP

Product Hunt Community Insights

BERT RoBERTa Python NLP

ML-powered sentiment analysis platform processing 368K+ user comments to surface product adoption drivers and engagement patterns

368K+ Comments
0.84 F1 Score
60% Time Saved
  • Architected automated NLP pipeline reducing manual processing time by 60% while improving data quality
  • Built multi-label BERT classifier achieving F1 0.84 across 7 categories and 14 subcategories
  • Conducted longitudinal trend analysis revealing key friction points and feature request patterns
  • Translated ML outputs into stakeholder-ready reports with actionable product recommendations
Code Available Upon Request

Experience

Hands-on data & analytics work across healthcare, higher education, and academia — building dashboards, models, and pipelines that stakeholders actually use.

Research Assistant — Human AI Empowerment (HAIE) Lab
Clemson University · ML / NLP · Product Analytics
May 2025 – Present · Remote / Clemson, SC
  • Analyzed 368K+ Product Hunt narratives to surface engagement patterns and product adoption drivers.
  • Built automated preprocessing pipelines, reducing manual processing time by 60% and improving data quality.
  • Developed multi-label BERT classifier (F1: 0.84) to structure feedback into 7 categories and 14 subcategories.
Graduate Assistant — Data Analytics
Clemson University Graduate School
Jan 2024 – May 2025 · Remote / Clemson, SC
  • Designed enterprise Power BI dashboards (DAX, M, star schema) to track enrollment, funding, and graduate KPIs.
  • Implemented RLS, automated refresh schedules, and version control for governed semantic models.
  • Partnered with VPs and Deans to align analytics outputs with strategic and operational priorities.
Data Science Intern — Data Visualization Lab
Clemson University Libraries
Aug 2023 – Jan 2024 · Clemson, SC
  • Built time-series forecasting models (≈85% accuracy) over 50K+ usage records to support resource planning.
  • Performed end-to-end ETL: wrangling, cleansing, SQL transformations, and feature engineering.
  • Developed interactive Power BI and Tableau dashboards adopted by non-technical stakeholders.
Senior Lecturer — Dept. of CSE (Study Leave)
Port City International University (PCIU)
Jan 2014 – Present (Study Leave) · Chattogram, Bangladesh
  • Taught database systems, data structures, and theory of computing at the undergraduate level.
  • Supervised 10+ student research projects in ML/AI and data-driven applications.
  • On study leave to complete MS and transition into full-time industry data & analytics roles.

Skills

A balanced stack across data engineering, analytics, BI, and ML — with a strong focus on clear communication and stakeholder value.

Data & Analytics

Python, SQL Advanced
dbt (models, tests, documentation), ETL/ELT workflows Advanced
MySQL, Oracle, DuckDB Advanced
Data Cleaning, EDA, KPI Development, Statistical Analysis, A/B Testing Advanced

BI & Visualization

Power BI (DAX, Power Query) Advanced
Tableau Intermediate
Star Schema & Semantic Models Advanced
Executive KPI Dashboards Advanced

ML, NLP & Cloud

ML (Logistic / Tree-based Models) Advanced
NLP (BERT / RoBERTa) Intermediate–Advanced
AWS (S3, EC2, RDS basics) Intermediate
Feature Engineering, Model Evaluation Intermediate
Prompt Engineering (ChatGPT, Claude, Llama), LLM fine-tuning, NLP pipelines Intermediate

Let’s Connect

I’m actively exploring Data Analyst, BI Developer, and Data / Analytics Engineer roles, with a strong interest in healthcare, higher education, and product analytics — especially in the Raleigh–Durham–Cary (RTP) area and remote-friendly teams.

Email: shahnajfujaila@gmail.com Connect on LinkedIn View GitHub