Overview GENERAL SUMMARY OF POSITION: The Associate Data Scientist is responsible for modeling complex clinical and research problems, discovering insights and identifying opportunities through the use of statistical, algorithmic, mining and visualization techniques. In addition to advanced analytic skills, this role is also proficient at integrating and preparing large, varied datasets, designing specialized database and computing environments, and presenting results. Data Scientists work closely with clients, project/program managers, and other IT teams to turn data into actionable information and knowledge that can be used to make sound organizational decisions. Core traits include creative thinking, innovative proposals, and expert data mining techniques. They will need to validate their findings using an experimental and iterative approach. In addition, he/she will perform diverse and complex duties in a manner consistent with a dynamic and active biomedical education and research community.
Responsibilities MAJOR RESPONSIBILITIES: Conduct innovative biomedical AI research, including multi-modal multi-task learning, transfer learning, deep representation learning, longitudinal modeling, and time series analysis. Aid with design experiments, test hypotheses, and build models Perform data analysis and moderately complex design algorithms. Work with team members to solve client analytic problems and document results/methodologies. Assist and perform experimental design approaches to validate finding or test hypotheses. Validate/Verify analysis by comparing appropriate samples. Use appropriate algorithms to discover patterns in complex datasets Perform other duties as assigned. Qualifications REQUIRED QUALIFICATIONS: Master's degree in Computer Science, Data Science, Informatics, a related field, or equivalent experience 1-3 years of experience in development and implementation of technologies Strong interpersonal and communication skills required Demonstrated ability to provide documentation Ability to communicate effectively in writing. Solid programming skills in Python, Java or C++. Proven experience with machine learning (deep learning), and natural language processing (NLP), including popular learning tools and frameworks, e.g., Pytorch, Scikit-learn, Huggingface, Langchain, etc. Experience in popular deep learning models (e.g., LSTM, CNN, Resnet, Transformer, Large Language Models) and deep tabular learning models (e.g., TabNet, TabTransformer) PREFERRED QUALIFICATIONS: PhD's degree preferred in Computer Science, Data Science, Biomedical Informatics, a related field U.S citizen or permanent resident preferred. Proven experience with electronic health records data and other clinical data Knowledge of AI model interpretability and fairness Familiar with research prototyping (e.g., user interface, dashboard) Strong writing skills with tracking records of publication
