University of Rochester

University of Rochester logo

Job Information

University of Rochester Data Scientist - 219589 in Rochester, New York

Data Scientist

Job ID

219589

Location

Medical Faculty Group

Full/Part Time

Full-Time

Favorite Job

Regular/Temporary

Regular

Opening

Full Time 40 hours Grade 053 Health Lab

Schedule

8 AM-5 PM

Responsibilities

Position Summary:

Assists Health Lab staff and collaborators in deriving knowledge from data. Responsible for exploring, obtaining, integrating, cleansing, visualizing, and modeling data. Performs data modeling using statistics, deep learning, and artificial intelligence techniques combined with domain research.

The data scientist will work closely with subject matter experts and with the engineering team to study and operationalize new healthcare interventions based on created data models.

Follows guidelines and directions given by the senior members of the team but has latitude for independent judgment and decision-making.

Responsibilities:

Project Management

  • Works with senior members of the team for projects to work on, requirements, and priorities

  • Explores health literature and data sources to determine what data to target

  • Determines an approach for which analysis techniques will be useful for each project

  • Reviews the project plan with senior members before implementation begins

  • Keeps senior members and constituents updated on project status

Data Acquisition

  • Researches data structures and data entry workflows to find accurate data

  • Runs SQL queries to gather data from various sources and store it in a usable format

  • Integrates otherwise disparate data elements so that they can relate to one another

  • Assists with the creation of labeled data sets for future projects

Data Cleansing

  • Uses tools such as R or Python to perform data cleaning

  • Transforms data into the appropriate format to be used with the desired algorithms

  • Imputes data as necessary for fields with missing values

  • Adheres to established standards and policy around de-identification of protected data

  • Documents the process so that results are reproducible and can be re-run with new data

Data Analysis

  • Uses tools such as R, Python, Azure ML, Caffe, TensorFlow, and/or Tableau to perform analyses

  • Uses statistics, clustering and data visualizations to find patterns in data

  • Works heavily with neural networks, natural language processing, and multimedia processing

  • Tries various models and evaluates the success or failure of each

  • Evaluates the effects of each data point on the overall model

Implementation

  • Assists senior members with the implementation of successful data models

  • Performs dimensionality reduction to reduce the complexity of models while maintaining accuracy

  • Makes models accessible to the software engineering team so that they can be integrated into end-user workflows

  • Develops an action plan for how the model will continue to learn over time

  • Works with leadership and other team members to analyze the efficacy of the implementation

Education and Training

  • Formally presents findings to leadership, co-workers, and collaborators and teaches them how results were achieved

  • Stays up to date on advances in computer science, deep learning, and artificial intelligence and incorporates that knowledge in future projects

    Qualifications:

Bachelor's degree in related discipline such as Computer Science, Business, Mathematics, Statistics, Science or Engineering, and 2-3 years of related experience; or an equivalent combination of education and experience.

Preferred Qualifications

Familiarity with Python, R or other data analysis tools such as SAS, Matlab, or Mathematica.

Experience with machine learning, statistics, data mining, data analysis, and data visualization.

This position requires a laptop (supplied).

How To Apply

All applicants must apply online.

EOE Minorities/Females/Protected Veterans/Disabled

DirectEmployers