Hi, I'mKhawaja
Data Analyst Intern @ Impiricus
I use code, queries and curiosity to turn raw data into real impact. Recently graduated from DePauw University with a BA in Computer Science with a concentration in Data Science.
Identified Revenue
Through rigorous data analysis in previous internship
Internships
Stealth AI/Tenzer Technology/DePauw University
Data Science Projects
Links below
Dean's List
Semester GPA > 3.50
Education
BA in Computer Science
DePauw University, May 2025
Minor in Data Science
DePauw University, May 2025
Skills Highlight
Data Engineering
ETL, Data Pipelines, Azure
Data Science
ML Models, Analytics, Visualization
Programming
Python, SQL, PySpark, JavaScript
Tools
Git, Docker, Jupyter, Power BI
Work Experience
Data Engineering Intern
Stealth AI
Dec 2024 - Feb 2025
San Francisco
- Architected an Azure data pipeline processing 10K+ financial transaction records daily, reducing KPI computation time by 40% and identifying $150K+ in recoverable revenue.
- Established PySpark validation frameworks that flagged 5K+ monthly anomalies, improving downstream analytics reliability by 35% for the finance team.
- Optimized cloud infrastructure with incremental ETL and dynamic scaling, cutting cloud costs by 20% while maintaining 99.9% SLA for 50K+ daily patient records.
- Resolved cross-hospital data inconsistencies using SCD2 dimensional modeling, increasing reporting accuracy by 28% and presenting actionable insights to CEO/CTO.
Data Analysis & AI Intern
Tenzer Technology Center
Feb 2024 - May 2024
Chicago
- Spearheaded the development of a reinforcement learning system for financial transaction forecasting that outperformed baseline models by ~11%, utilizing RAGAS framework to evaluate the LLM.
- Designed A/B testing frameworks for user experience optimization, resulting in a 22% improvement in Click-through rate and a ~6% decrease in bounce rate
- Implemented CI/CD pipeline with automated testing that reduced deployment time from days to hours, enabling rapid iteration across 3 development cycles.
- Delivered critical production fixes that resolved performance bottlenecks, accelerating system response time by 15% under peak loads.
Data Science Intern
Depauw University
Oct 2023 - Jan 2024
Greencastle
- Built an automated sports analytics platform using Python and pandas that integrated 5+ data sources, delivering insights that improved team performance by 23% across 12+ competitions.
- Designed custom Git-versioned ETL & EDA workflows processing 300+ player statistics daily, reducing analysis latency by 80%.
- Developed statistical research for predictive models with 85% accuracy that identified 7 high-potential recruits
My Projects
Here are some of my recent projects that showcase my skills in Data Engineering, Data Science, and Analytics.
Transportation Time Series Data Dashboard
Developed forecasting models analyzing transit patterns to predict future demand, delivering actionable recommendations that translated statistical findings into measurable business value while optimizing resource allocation and reducing operational costs.
Healthcare Revenue Cycle Management Optimization
Conducted statistical analysis to optimize the revenue cycle management pipeline, identifying $2.4M in potential recapture opportunities and delivering actionable recommendations that reduced claim denials by 22% while improving the overall financial metrics of the healthcare facility.
Lyft Driver Supply Optimization
Built an interactive platform using real-time ride-hailing data (92M+ trips) to forecast 30-minute demand with 87% accuracy, uncovering $3.2M/month in missed revenue. ML-driven strategies improved driver-rider matching—boosting market balance by 9%, cutting incentive spend 4%, reducing wait times up to 10%, and increasing driver earnings by 14%.
Agtech Agricultural Pipeline
Engineered a scalable ETL pipeline that ingested and normalized IoT sensor data from 200+ field devices using Python, SQL, and Apache Airflow, enabling real-time crop yield predictions.
Statistical Analysis of Graduate Debt
Conducted in-depth statistical analysis comparing average debt of graduates from small private universities with large private universities using R/RStudio, revealing significant patterns in student loan burdens.
Reinforcement Learning Game
Developed a game with an AI opponent that progressively improves using reinforcement learning. Players take turns removing 1-4 sticks from a pile, with the player who takes the last stick winning. The AI agent learns optimal strategies through gameplay.
My Skills
Data Engineering
Data Science
Machine Learning
Programming
DevOps & Tools
Get in Touch
Have a question or want to work together? Feel free to contact me!
Contact Information
I'm currently seeking full-time roles in Data Engineering, Data Science, or Analytics where I can continue learning and building impactful systems. Whether you have a question or just want to say hi, I'll try my best to get back to you!
ahmed.khawaja.hussain@gmail.com
Location
New Jersey
Phone
(702) 348-9820
Let's Connect
Phone
(702) 348-9820
Prefer email? You can reach me at:
ahmed.khawaja.hussain@gmail.com