Deep Learning

This project demonstrates proficiency in designing, training, and analyzing custom Convolutional Neural Networks (CNNs). We developed and compared two distinct model architectures—a Sequential baseline and a Functional API model with Batch Normalization (BN)—to assess the impact of architecture design and optimization strategy (Adam vs. SGD) on classification accuracy and training stability for low-resolution color images.

CNN is the architecture I want to use to on the electric vehicle detection problem. Ask me about the advantages.

Notebook available upon request (I love talking about how to tune these things)

Agentic AI

I bridge the gap between Strategic Analytics and AI Automation. Beyond traditional predictive modeling, I design and prototype Agentic AI systems—intelligent workflows capable of reasoning, tool use, and task execution.

What I Build:

• Smart Orchestration: Systems that can translate business emails into Jira tickets or technical tasks.

• Legacy Code Refactoring Agents: Workflows that ingest legacy scripts (SAS/R), map the logic, and draft modern Python replacements.

• Governed Digital Workers: Automated agents that perform low-level data operations (QA checks, report generation) under strict human supervision.

I combine the statistical rigor of a traditional Data Scientist with the engineering mindset of a developer to build AI that works safely in the enterprise.