Summary
Yanxi Li is an Information Technology Consultant and PhD-track computational linguistics researcher with 10 years of engineering experience, now applying LLMs and VQA techniques to real-world risk and document analysis at the Inter-American Development Bank. She has built production-grade LLM pipelines—combining GPT-4o, RAG/vector stores, Streamlit, Flask, and Azure services—to continuously surface and refine risk signals across large institutional document collections and news feeds. Earlier roles as a data engineer focused on scalable ETL, distributed crawling, and similarity metrics for heterogeneous text pools, with practical deployments using MongoDB, Airflow, and multithreaded crawlers. Her work blends hands-on systems engineering with a research emphasis on model interpretability and prompt engineering, and she brings cross-lingual fluency (English/Spanish) to language-centric AI problems. An uncommon strength is translating cutting-edge LLM research into audit-ready workflows that align with institutional taxonomies and governance.
10 years of coding experience
1 year of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at The George Washington University
Bachelor of Engineering - BE, Computer Science & Engineering, Bachelor of Engineering - BE, Computer Science & Engineering at Chengdu University (CDU)