Hi, I'm
Delphin Kaduli
I build end-to-end machine learning systems and automated data platforms that optimize operations and protect financial infrastructure from risk. I design robust models engineered for production cloud deploymen, not just a notebook.
Available for hire
About Me
I started by trying to understand how systems behave. What began as curiosity about patterns and signals grew into a lifelong commitment to building technical solutions that deliver absolute clarity and automated confidence.
Today, my primary focus centers on fraud detection, risk analytics, and the modern data architectures that power them. I build for production, not just a notebook, ensuring clean pipelines, optimized features, and resilient model deployments. My engineering discipline is grounded in a mindset shaped by faith, family, and movement. I truly believe that exceptionally designed systems outperform isolated efforts, and I bring that collaborative, mission-driven approach to every team.
Looking ahead, I am driven by one foundational question: Does this system help someone make a better call? That is the standard of excellence I build toward from data ingestion and automated validation to hyperparameter optimization and cloud deployment.
Projects
My work focuses on the intersection of Fraud Detection, Risk Analytics, Predictive Systems, and Data Engineering.
Fraud Detection System
Delivered 0.93 Precision and 0.82 Recall on a 0.17% imbalanced dataset, ensuring 93% of flagged transactions are confirmed fraud to mitigate financial loss.
Demand Forecasting System
Achieved a 51% MAE reduction by developing a real-time demand forecasting system on AWS to optimize dynamic pricing and fleet utilization.
Metro Transit Analytics
Engineered a production-ready Medallion data platform using Apache Airflow and PostgreSQL to process 1M+ real-time transit records, maintaining a 76.1% data yield across 8 automated quality gates.
Technical Skills
Tools and technologies I use to build production-ready data systems
Python (Pandas, NumPy, Polars)
SQL (CTEs, Window Functions, Optimization)
ETL Pipelines (Airflow, Medallion Architecture)
Data Quality, Validation & Monitoring
Power BI & Tableau (DAX, Dashboards)
Data Warehousing (Snowflake, PostgreSQL)
Core Tech Stack
Python
SQL
PostgreSQL
Snowflake
AWS
Airflow
Docker
Scikit-learn
MLflow
FastAPI
Streamlit
Power BI
GitHub
Tableau
NumPy
Pandas
Experience
Professional Impact & Results
Data Scientist & Research Analyst
The Catholic University of America
Jan 2024 - Dec 2025
Contract / Research Fellow
Data Infrastructure Engineer
Women of Faith
Jul 2021 - Dec 2023
Full-time
What I'm Learning Now
Continuous growth in production ML and data engineering
Deep Learning & NLP
Building neural networks for text classification, sentiment analysis, and language understanding with PyTorch and Transformers.
Model Monitoring & Drift Detection
Implementing drift alerts, performance dashboards, and automated retraining triggers.
Feature Stores & Real-Time ML
Exploring Feast and online feature pipelines for fraud detection and low-latency scoring.
AWS Step Functions & Event-Driven Pipelines
Designing serverless workflows that orchestrate ML systems with reliability and traceability.
Advanced Airflow Patterns
Building more resilient DAGs, improving observability, and applying data quality checks at scale.
Contact Me
Let's build something Amazing