We are currently seeking a Data Scientist to help us mine information from our rapidly growing set of clinical data. The insight gained from these mining expeditions will help us understand the impact that our technology is having on critical care, determine new use cases for the technology, and develop future versions with more advanced capabilities. You will be tasked with a range of responsibilities, including data mining, statistical analysis, model development, database curation/augmentation, publication and collaboration with partnering academic medical centers.
Responsibilities
- Manipulate large data sets consisting of patient clinical data and outcome data.
- Mine patient data for critical events, outcome variables, and treatment actions.
- Perform statistical analysis to understand relationships between clinical variables and Etiometry’s Risk AnalyticsTM
- Develop models for prediction and classification utilizing machine learning techniques such as logistic regression, SVMs, neural networks, decision trees etc.
- Provide data mining and analysis support, including data cleaning, to data customers, which includes other Etiometry teams and research collaborators from partnering hospitals.
- Research current advances in data science and statistical analysis methods.
- Publish analysis findings at data science conferences and in journals.
Basic Qualifications
- Master’s Degree, or Bachelor’s Degree with 3 years of experience, in engineering, computer science, statistics, bioinformatics, or other related field.
- Strong background in statistical analysis, machine learning, and data mining including regression analysis, classification, predictive modeling, feature engineering, hypothesis testing etc.
- Solid understanding of probability theory and statistics.
- Experience manipulating large data sets of time-series and intermittent data.
- Strong communication and organization skills.
- Proven ability to contribute to emerging or cross-disciplinary fields.
Desired Qualifications
- Experience working with Python as a development language with an emphasis on data science.
- Experience with Python data analysis packages such as Sci-kit Learn, Pandas, and SciPy.
- Comfortable working in a Linux based environment.
- Experience working with database types such as MongoDB, MySQL, and PostGres.
- Knowledge of Bayesian data analysis methods such model comparison, Markov Chain Monte Carlo sampling , Hierarchical modeling, Generalized linear models, and Bayesian networks.
- Experience working with clinical data.
- Experience performing independent research projects.
by via developer jobs - Stack Overflow
No comments:
Post a Comment