Summary
Jane Jiang is a Data Engineer and AI practitioner with nine years of experience building agentic systems, retrieval platforms, and scalable AI infrastructure, currently at Argonne National Laboratory. She has hands-on expertise applying advanced algorithms like HNSW for multi-source JSON integration and deploying local Llama3 agent frameworks to convert unstructured text into structured JSON for downstream analysis. Previously she developed end-to-end GenAI products and graph representation learning pipelines, and her work spans model fine-tuning, few-shot learning, and production-focused performance optimizations. Jane has a strong background in applied ML and big-data engineering—using XGBoost, PySpark, and TensorFlow—to drive measurable improvements such as halving run times and boosting model utility for clinicians. Trained at Carnegie Mellon with academic stints at Xiamen, Colgate, and Cornell, she blends economics, business analytics, and computer science perspectives to solve practical problems. Outside engineering, she balances curiosity for new AI applications with simple pleasures like swimming and movie-watching, reflecting a grounded, experimental approach to research and productization.
9 years of coding experience
1 year of employment as a software developer
Exchange Student Economics & Computer Science, Exchange Student Economics & Computer Science at Colgate University
Summer Program Applied Economics and Management, Summer Program Applied Economics and Management at Cornell University
Master’s Degree Information System Management-Business Intelligence and Data Analytics, Master’s Degree Information System Management-Business Intelligence and Data Analytics at Carnegie Mellon University
Bachelor’s Degree Economics, Bachelor’s Degree Economics at Xiamen University