[Thomas Jefferson University Hospital] Data Scientist

替前老板发贴招人: Thomas Jefferson University Hospital 是位于费城的一家全美Top20综合性医院(偶尔年份能到Top10),   Data Scientist职位位于医院Informatics Department下面的Data Science Team. 老板是华人, 人很nice. 工作内容主要是医疗大数据, pay可能比不上大厂, 但医院各种福利很好, 工作轻松且非常稳定,基本不会fire人. 另外大学医院解决身份比较容易.  感兴趣请直接发信给hiring manger, Michael.Li@jefferson.edu

Senior Data Scientist:

PRIMARY FUNCTION:  Senior Data Scientist will support the Director of Data Science in coordinating, advocating for, and diffusing data science techniques across the enterprise. The individual will lead efforts in the organization’s analytical and predictive capabilities available in support of Jefferson’s mission and vision He/she will advise and execute on the ML-Ops strategy; Statistical and Predictive Modeling; Combine AI/ML and Engineering skills to implement highly scalable platform components and tools to solve real-world problems in areas such as Image Recognition, Text Recognition, Natural Language Processing, Best Next Action, and Time Series predictions. Reporting and Data Visualization development.

ESSENTIAL FUNCTIONS:

Lead in the development of high-impact tools for ad hoc projects and on-going advanced analytics platforms.
Support the organization’s advanced analytics strategic objectives.
Drive implementation of the standards and methods for creating Predictive Models
Help develop a predictive model solution framework to integrate the following components: ODS, Machine Learning, APIs, scorecards, dashboards, reporting tools, as well as complimentary tools.
Epertise in Machine Learning, Microsoft Azure, R, Python, etc. Logically organizes large amounts of data and conceptualizes how they may be integrated and associated together to provide meaningful insight
Develops and maintains documentation including ML/AI standards and routines. Interacts with co-workers, visitors, and other staff consistent with the iSCORE values of Jefferson.

EXPERIENCE REQUIREMENTS:
3+ Year using Python/R/etc to conduct advanced statistical analyses (i.e., A/B Testing) & multivariate analysis, building predictive models.
Hands on experience on ML algorithms (linear / logistic regression, SVMs, Tree-based models, NLP, CNN, RNNs) and their real-world pros/cons to improve performance, efficiency and techniques (cross validation, feature selection approaches, hyper parameter optimization etc.)


ADDITIONAL INFORMATION:

Ability to mentor, motivate and set clear goals for junior team members.
Strong initiative, self-motivation and the ability to work both independently and in teams
Demonstrated ability to work effectively and collaboratively with others
High degree of professionalism, a positive ‘can do’ attitude and strong work ethic
Willing to go above and beyond to ensure achievement of goals
Strong customer service orientation
Organizational skills to handle several projects simultaneously and to accommodate shifting priorities and meet deadlines
Effective communication, presentation and facilitation skills
Demonstrated strength in critical thinking to identify new system solutions for evolving business requirements
Experience with health data and products is highly preferred
Exposure to most of the following: Orchestrate (Kubeflow Pipelines, MLRun), Container (Docker, Kubernetes), Model Serving (Kubeflow KF Serving, TF Serving), ML framework/tools (TensorFlow, Keras, ScikitLearn, Spark, etc.), and Feature Stores
Experience with AI/ML Governance: Model Repository (MLflow Registry, ModelDB), Code Repository (GitHub, etc.), Model Tracking (MLflow Tracking, TensorBoard), Explainable AI ( LIME, SHAP, etc.), and Fairness (TensorFlow Fairness Indicators, FairLearn)
Experience architecting solution components for business intelligence and Machine Learning
Demonstrated strength in critical thinking to identify new predictive models for evolving business requirements
Experience in Stakeholder engagement and delivering decision-impacting metrics for specific departments, divisions, and the enterprise.
Experience using an agile development methodology
Experience with project management and change management tools such as JIRA


Data Scientist:

PRIMARY FUNCTION:



The Data Scientist supports the department by delivering a wide range of analytics projects.

The successful candidate will work with different types of data, including EMR/EHR data, claims data, consumer data, operation and HR data, education data and etc.  Also provides analytic consulting support outcome and quality research, population health, clinical and academic research, internal clinical and operational decision support initiatives. The scientist is charged with data processing, data mining, statistical modeling, analysis, extracting insights and problem solving.



ESSENTIAL FUNCTIONS:



Perform data processing and manipulation, data analysis, coding and programming using SAS, R or other tools.  Develop and test models
Explore different internal data and assess feasibility for advanced modeling
Execute projects and solve analytics problems
Analyzes, synthesizes descriptive and modeling results to provide insights
Prepare deliverables and communicate the findings and results
Interact with co-workers, visitors, and other staff consistent with the iSCORE values of Jefferson.


OTHER FUNCTIONS AND COMPETENCIES:

Develop statistical analyses, data processing, text and unstructured data analyses, and data mining solutions.
Data mapping, cleaning, merging, extracting and etc.
Gather, organize, and document descriptions of data assets for supporting various research.
Document methodology, process, findings, and insights.
Perform literature search and research (academic and commercial), and crystalize findings.
Participate and perform analytics tasks in areas such as predictive and prescriptive modeling, health economics, risk modeling, outcomes research, program evaluation studies, customer analytics, sentiment analyses, operations research and workflow modeling, product development, and ad-hoc analyses.

请问是on-site, hybrid, 还是remote? 谢谢

已发邮件zhihao.**@....，谢谢您提供的机会