Xuanjie G is a Bioprocessing Associate III with nine years of experience in upstream clinical manufacturing and biologics process characterization, currently supporting on-floor operations at WuXi Biologics in New Jersey. With hands-on expertise in fed-batch and perfusion bioreactors, cell banking management, and BSL-2 vaccine studies, they bridge lab execution with data-driven insights, routinely performing statistical analysis and electronic lab record stewardship. Xuanjie has led internal technical projects and cross-department training, and also supports analytical assays such as automated western blot, reflecting a strong aptitude for both process and analytical collaboration. Unusually for a bioprocess professional, they contribute to NLP model development on GitHub—implementing LSTM-CRF NER models within the high-profile ModelScope repository—demonstrating a rare combination of wet-lab rigor and machine learning engineering. A meticulous, adaptable quick learner with an MS in Biomedical Engineering, Xuanjie thrives working independently or as a team member to translate complex experimental data into actionable outcomes.
9 years of coding experience
3 years of employment as a software developer
Master of Science - MS, Biomedical Engineering, 3.85, Master of Science - MS, Biomedical Engineering, 3.85 at Drexel University School of Biomedical Engineering, Science and Health Systems
High School, High School at Middleschool Attached to Sun-Yatsen University
ModelScope: bring the notion of Model-as-a-Service to life.
Role in this project:
ML Engineer
Contributions:3 commits, 4 PRs in 6 months
Contributions summary:Xuanjie contributed significantly to the implementation of Named Entity Recognition (NER) models within the ModelScope repository. This included adding code for LSTM-CRF NER models, including the necessary dependencies, classes and tests. The user also updated the NER preprocessor to handle specific scenarios and integrated prompt-based models. These changes enhance the repository's capabilities in the domain of natural language processing.
Code for 'Prototypical Representation Learning for Relation Extraction'.
Contributions:4 commits, 3 pushes, 1 branch in 1 month
relation-extractionrepresentation-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.