Experience

Calculated Systems

• United States
• IT Services and IT Consulting
• 1 - 100 Employee

• Data Scientist

  • Jun 2022 - Mar 2023

  • Led the design and implementation of real-time social media analytics toolkit. Built robust Natural Language Processing pipeline by CoreNLP, NLTK and HanLP on large volume of streaming data, approx. 150 million feeds per day. Deployed on GCP using Docker and Cloud Run. • Developed real-time hot topic extraction, detection, and summarization pipeline using Python, Jupyter Lab and Google Pub/Sub, capable of customized tuning and filtering. Set up Postgres database for ETL. • Trained and… Show more • Led the design and implementation of real-time social media analytics toolkit. Built robust Natural Language Processing pipeline by CoreNLP, NLTK and HanLP on large volume of streaming data, approx. 150 million feeds per day. Deployed on GCP using Docker and Cloud Run. • Developed real-time hot topic extraction, detection, and summarization pipeline using Python, Jupyter Lab and Google Pub/Sub, capable of customized tuning and filtering. Set up Postgres database for ETL. • Trained and Tuned Neural Machine Translation models based on Bi-directional GRU in TensorFlow via Jupyter Lab and Vertex AI on Google Cloud Platform. Using creative tokenization methods to translate Chinese language. Achieved high accuracy of 0.9 on validation data built from social media texts. Show less • Led the design and implementation of real-time social media analytics toolkit. Built robust Natural Language Processing pipeline by CoreNLP, NLTK and HanLP on large volume of streaming data, approx. 150 million feeds per day. Deployed on GCP using Docker and Cloud Run. • Developed real-time hot topic extraction, detection, and summarization pipeline using Python, Jupyter Lab and Google Pub/Sub, capable of customized tuning and filtering. Set up Postgres database for ETL. • Trained and… Show more • Led the design and implementation of real-time social media analytics toolkit. Built robust Natural Language Processing pipeline by CoreNLP, NLTK and HanLP on large volume of streaming data, approx. 150 million feeds per day. Deployed on GCP using Docker and Cloud Run. • Developed real-time hot topic extraction, detection, and summarization pipeline using Python, Jupyter Lab and Google Pub/Sub, capable of customized tuning and filtering. Set up Postgres database for ETL. • Trained and Tuned Neural Machine Translation models based on Bi-directional GRU in TensorFlow via Jupyter Lab and Vertex AI on Google Cloud Platform. Using creative tokenization methods to translate Chinese language. Achieved high accuracy of 0.9 on validation data built from social media texts. Show less



Manulife-Sinochem Life Insurance Co. Ltd

• Shanghai, China

• Actuarial Intern

  • Jan 2021 - Mar 2021

  • Created and adjusted statistical models for price calculations and predictions. Worked on large scale and complex Bayesian probability models in R. • Supported finalizing pricing and strategy for multiple new products before release in February 2021. • Created and adjusted statistical models for price calculations and predictions. Worked on large scale and complex Bayesian probability models in R. • Supported finalizing pricing and strategy for multiple new products before release in February 2021.



Shanghai Bestudy Medical Technology Co., Ltd

• China
• Pharmaceutical Manufacturing
• 1 - 100 Employee

• Data Analyst Intern

  • Jul 2020 - Oct 2020

  Handled data cleaning, processing, and visualization for raw medical research data through Tableau and Microsoft Power BI. Handled data cleaning, processing, and visualization for raw medical research data through Tableau and Microsoft Power BI.