Today, when you go to your doctor and need to be referred to a specialist (e.g., for sleep apnea), your doctor sends a fax (yes, in 2024, 90% of provider to provider communication is a 1980s fax). These are often converted into 20+ page PDFs, with handwritten (doctor’s handwriting!) notes, in thousands of different formats. The problem is so complex that a person has to read it, type it up, and manually enter your information. Tennr built RaeLM™ (7B—trained on 4M+ documents) to read these docs, talk to your doc to ensure nothing is missed, and text you to help schedule your appointment so you can get better, faster.

- Developed bug-finding algorithm to clean company datasets; generated building-polygon dataset and interactive geospatial maps; built client-content web scraper; performed topic modeling on text documents to analyze client content- Worked on chat bot to assist user experience; implemented vector stores to provide bot with relevant company data; processed client content to develop a brand voice for the bot- Implemented ontology tables as a foundation for company software; built mapping table to standardize sector KPI benchmarks across media channels- Presented plan to monetize and structure future data streams to CEO and team leads- Tools: Python, Pandas, GeoPandas, Folium, Beautiful Soup, LangChain, Excel

10-week intensive program to develop and launch a startup venture

Designed novel optical circuit to perform quantum computing algorithm working under Professor Claire Gmachl.