DATA SCIENCE · AI · SOFTWARE ENGINEERING

Building intelligent systems from data pipelines to working applications.

I build across machine learning, deep learning, generative AI, NLP, data engineering, automation, operational analytics, model validation, REST APIs, relational databases, and application development. This portfolio focuses on complete technical work: problem formulation, architecture, code, validation, testing, limitations, and engineering decisions.

9Technical projects
AI → AppsEnd-to-end scope
Evidence-ledTransparent provenance
SELECTED WORK

Projects

The repositories separate recovered historical work from reconstructed and enhanced components, so implementation claims remain technically defensible.

TECHNICAL RANGE

Capabilities

AI & Machine Learning

TensorFlow, Keras, CNNs, transformers, Hugging Face, prompt engineering, Sentence-BERT, HDBSCAN, interpretable ML, calibration, subgroup validation, and model evaluation.

Data Engineering & Analytics

Python, Pandas, semi-structured data processing, ETL, feature engineering, statistics, anomaly detection, public-health analytics, operational validation, and reporting.

Backend & Databases

Flask, REST APIs, SQL, PostgreSQL, SQLite, MySQL, SQLAlchemy, Alembic, relational modeling, transactions, RBAC, concurrency controls, migrations, and automated testing.

Application Engineering

TypeScript, Docker, Docker Compose, service-to-service integration, browser/client runtime boundaries, PDF processing, financial analytics, adaptive rules, debugging, and layered application architecture.

ENGINEERING APPROACH

Evidence over embellishment.

My portfolio emphasizes complete technical reasoning: how data are structured, why an algorithm is appropriate, what assumptions the system makes, where the implementation can fail, and how results should be interpreted. Historical work and modern reconstructions are explicitly separated so the repositories remain accurate and defensible.

RECOVEREDSupported by prior work, records, or artifacts.
RECONSTRUCTEDFaithfully rebuilt when original source bytes were unavailable.
ENHANCEDModern engineering improvements added for portfolio quality.
UNVERIFIEDNot presented as historical fact without evidence.
PROFESSIONAL PROFILES

Explore my work and experience.

Review the implementation on GitHub or connect through LinkedIn for professional experience and updates.