Employment
- Feb 2026 - present: Senior Healthcare Data Scientist, University of Maryland Medical System, Linthicum, MD, USA
- Technical Strategy and Architecture: Directed technical roadmaps and architected unified analytics platforms for mission critical enterprise applications, translating executive priorities into scalable AI initiatives, with hands on involvement in core modeling and critical path implementations to ensure decisions are grounded in production realities.
- Cross Functional Delivery and Scaling: Served as the primary data science liaison across clinical, product, and application engineering teams, leading design reviews and hands on technical discussions to scale analytics initiatives from concept to production.
- Executive Communication and Impact Reporting: Partnered with senior leadership to communicate outcomes, tradeoffs, and lessons learned through concise reports, presentations, and stakeholder facing materials focused on value, impact, and evaluation metrics.
- Mentorship and Team Development: Mentored data scientists through onboarding, knowledge sharing, and guided walkthroughs of core modeling frameworks and analytics platforms to elevate team capability and technical maturity.
- Intellectual Property and Innovation: Led innovation initiatives and contributed to intellectual property development by formalizing system designs, modeling approaches, and platform level capabilities supporting long term differentiation.
- May 2021 - Feb 2026: Healthcare Data Scientist, University of Maryland Medical System, Linthicum, MD, USA
- AI and Operations Research Modeling: Designed and deployed advanced predictive and optimization models powering large scale clinical and operational decision support systems.
- MLOps Ecosystem: Engineered standardized modeling frameworks and configuration driven pipelines to support scalable training, deployment, and monitoring of production models.
- Real Time Data and Application Infrastructure: Co-designed and built real time EMR/EHR pipelines through HL7 and RWB, and developed analytics ready data layers, ORM based data access layers, and application facing views that power downstream APIs and real time analytics applications.
- Enterprise System Reliability and Technical Leadership: Led cross team technical coordination across data science, data engineering, and full stack teams to improve platform resiliency through refactoring, dependency mapping, and end-to-end debugging across data, modeling, and application layers.
- May 2020 - May 2021: Graduate Research Assistant, The Ohio State University, Columbus, OH, USA
- Processed large scale mobility and geospatial datasets from SafeGraph to support epidemiological simulation modeling and public health analytics. [report link]
- Built scalable geospatial data compression and visualization workflows using Mapbox Tippecanoe and Mapbox GL JS to analyze large volumes of COVID simulation outputs.
- Implemented statistical and spatial analysis methods in R to identify high risk and actively transmitting populations across multiple geographic levels.
- Led development of a production COVID-19 surveillance platform for the Ohio Department of Health, including data architecture, interactive applications, and epidemiological models such as EWMA, space-time permutation scan statistics, and Bayesian spatio-temporal nowcasting model.
- Delivered a school-focused COVID analytics and surveillance system supporting data informed decisions across 20+ school districts.
- Aug 2016 - May 2020: Graduate Research Assistant, The Ohio State University, Columbus, OH, USA
- Led the OSU research team in collaboration with the ROSEN Group to develop interpretable AI models for anomaly detection in oil and gas pipelines, using Magnetic Flux Leakage in line inspection data with both signal and imaging modalities from advanced inspection instruments.
- Designed and deployed a cyber vulnerability prioritization scoring system, covering data fusion, model development, and applied product design to support early risk assessment and mitigation.
- Developed decision making models under uncertainty using Partially Observable Markov Decision Processes, Bayesian Reinforcement Learning, and Discrete Event Simulation to optimize inspection and maintenance policies for cybersecurity operations.
- Co-authored peer reviewed journal articles and presented research at academic conferences in operations research, machine learning, reinforcement learning, and simulation.
- Mentored 20+ undergraduate and graduate students on research and course projects in data science, machine learning, and optimization.
Skills
- Leadership: Hiring and team development, Technical mentorship, Project roadmapping, Pilot to production execution, Cross stakeholder communication, Executive level presentations.
- Data Tech: PostgreSQL, MySQL, SQL Server, Epic Clarity data structures, HL7 interfaces, Real time EMR feeds including RWB, Common Data Repository architecture, Data modeling, ETL pipeline design, Workflow orchestration with Airflow, Materialized view design and refresh strategies, Data lineage and dependency tracing, Query optimization for performance and reliability
- Visualization: Streamlit, R Shiny, Plotly, Mapbox GL JS, Leaflet, Matplotlib, Seaborn, visNetwork, Interactive web-based dashboard development
- Modeling: Supervised & unsupervised learning, Time series modeling, Imbalanced classification, Hyperparameter tuning, Reinforcement learning, Production deployment with CI/CD automation, Pyomo-based optimization, Discrete event simulation, Statistical analysis, NLP processing, LLM-based applications
- Programming: Python, R, SQL, Matlab, GAMS
- Libraries:
- Python: pyomo, Gurobi API, Cplex API, simpy, scikit-learn, imbalanced-learn, xgboost, hyperopt, keras, NLTK, tokenizers, langchain, OpenCV, skimage, numpy, scipy, pandas, matplotlib, plotly, Flask, sqlalchemy, streamlit, airflow
- R: caret, DMwR, MDPtoolbox, pomdp, ompr, CVXR, dLagM, rsatscan, tidyverse, leaflet, visNetwork, odbc, shiny, shinyjs
- Matlab: Cplex Class API
- Software: ARENA, Simio
- Others: LaTeX, Microsoft Office Suite
Awards
- 2019: Runner-up, Student Paper Competition, The Social Media Analytics Section of INFORMS.
- 2014: Second Prize of Scholarship for Excellent Students, Jinan University.
- 2013: Third Prize of Scholarship for Excellent Students, Jinan University.
- 2013: Yihai Kerry Scholarship for Innovative Undergraduates, Jinan University.
- 2013: Meritorious Winner, National College Mathematical Contest in Modeling.
- 2012: First Prize, China Undergraduate Mathematical Contest in Modeling.