👋 About Me

I am an applied machine learning engineer with experience in predictive analytics, forecasting, and decision optimization. I enjoy building systems that turn complex modeling work into clear, practical outcomes for real business and research settings.

My work spans Python, SQL, experimentation frameworks, data pipelines, monitoring systems, and modern ML/AI tooling. I have worked across reinforcement learning, financial modeling, cybersecurity, RAG systems, and predictive analytics, with a focus on shipping end-to-end solutions that improve efficiency, resource allocation, and decision quality.

I recently completed my M.S. in Data Analytics and Engineering at George Mason University and remain especially interested in the space between analytics, applied AI, and scalable decision systems.

What I’m Working On

• Building reinforcement learning systems for non-stationary financial markets
• Exploring LLM reasoning efficiency and post-training optimization
• Designing agentic AI workflows for cybersecurity and enterprise knowledge use

Selected Highlights

• Improved portfolio robustness in a regime-aware RL system, increasing alpha from approximately +0.05 to +0.23
• Built LLM-assisted cybersecurity workflows using SecureGPT, AWS Lambda, and NIST-grounded prompting
• Developed adaptive trading strategies that improved annualized returns from 18% to 25%
• Published work in NLDB 2025 and IEEE INDICON 2022