Career Summary

Machine learning systems for structured scientific and technical problems, with emphasis on graph-based models, biological systems, and reproducible research pipelines.

• Graph neural networks and structured ML
• Protein structure networks and molecular representations
• Agentic workflows and multi-step reasoning systems
• Scientific ML tooling and pipeline design 
• Local compute infrastructure for reproducible research

• Designing and implementing graph-based representations of protein structures
• Developing agentic ML workflows for scientific analysis and reasoning
• Building modular, inspectable pipelines for computational biology and related domains
   

• Ongoing coursework in machine learning, graph-based models, and deep learning
• Independent study in computational biology, protein structure, and molecular systems
• Applied work focused on translating theory into usable research tools