About
Recent Barrett Honors graduate working on moonshot protein interaction research at Mayo Clinic and developing machine learning models for bioinformatics. My research focuses on protein language models, remote homology detection, and 3D mesh segmentation. I'm a key contributor to the scikit-bio library, published in Nature Methods, and have worked on ML applications at Wells Fargo and the U.S. Department of State.
Skills
Work Experience
Focused on machine learning research and computational biology. From protein language models to transformer architectures.
TM-Vec: Protein Language Model Optimization
Re-trained protein language model (pLM) architecture TM-Vec for remote homology detection, achieving 50x speedup in inference time. Integrated model into scikit-bio for bioinformatics workflows and structural similarity analysis.
Multi-PDF RAG Chatbot
Built retrieval-augmented generation (RAG) system using LangChain agent workflows and FAISS vector database for multi-document question answering with semantic search.