Associate Data Scientist

University of Southern California•Los Angeles, CA

7d•$99,824 - $100,000

About The Position

The Department of Population and Public Health Sciences at the University of Southern California (USC) invites applications for an Associate Data Scientist position supporting research in environmental health, exposomics, air pollution, and geospatial methods for modeling environmental and extreme weather-related exposures and their health impacts across the life course. This position offers opportunities for interdisciplinary collaboration and professional development, including co-authorship on publications, presentation at scientific conferences, and involvement in grant-funded research projects. Areas of scientific investigation include methods development around extreme weather and health, electronic medical record mining, large scale geospatial, remote sensing, and multimodal data integration and analysis, mobility and activity space analysis, and standardization of exposomics data pipelines. Additional areas of interest may include the joint modeling of multiple exposures and interactions with community- and individual-level adaptation and resilience factors on health outcomes. The successful candidate will use analytical, statistical, and programming skills to collect, analyze, and interpret large and complex data sets, and will assist with identifying data-analytic problems, determining the correct data sources, and developing solutions. Individuals with strong technical skills in statistical programming, data modeling, and machine learning – particularly as applied to exposure science, geospatial analysis, remote sensing, or population health – will be given strong consideration. The ideal candidate is a well-rounded, detail-oriented individual who can work independently but also thrives in and contributes to interdisciplinary, collaborative team settings.

Requirements

Bachelor’s degree in Applied Mathematics, Geography, Computer Science, Statistics, or a related quantitative field (or equivalent experience)
Minimum 2 years of experience in data science, data analytics, or a related field
Proficiency in Python and SQL for data analysis and data manipulation
Experience working with relational and/or non-relational databases (e.g., MySQL, SQL Server, Snowflake, MongoDB)
Experience performing data cleaning, transformation, and validation
Demonstrated ability to analyze datasets and deliver actionable insights
Strong written and verbal communication skills

Nice To Haves

Master's degree or PhD in Geography, Statistics, Environmental Health, Remote Sensing, or a related field
5+ years of relevant work experience in exposure data science, geospatial analytics, or a related field
Experience using statistical computer languages (e.g., SAS, R, Python, SQL) to manipulate data and draw insights from large data sets especially spatial data sets (e.g. Python, ESRI suite)
Experience working with and creating data models and data architecture, and using data visualization tools (e.g., Tableau, ArcGIS, D3.js)
Knowledge of current data modeling tools and machine-learning techniques (e.g., clustering, decision-tree learning, artificial neural networks)
Proficiency with query languages (e.g., SQL, MDX) and experience with relational (e.g., MySQL, SQL Server, Snowflake, Redshift) and non-relational (e.g., MongoDB, NoSQL) databases and cloud environments
Knowledge of applied statistical concepts and techniques (e.g., distributions, statistical testing, regression)
Ability to write high-quality, well-documented SAS/Python code, with familiarity in unit testing, source control, and code review
Excellent written and oral communication skills, including the ability to summarize findings for both technical and non-technical audiences
Demonstrated interest in data science and artificial intelligence; open-domain contributions (e.g., GitHub) and/or published writing in data science are a plus

Responsibilities

Create, analyze and interpret large datasets to support research goals and solve data analytic problems
Build, test, and optimize statistical, predictive, and machine learning models
Develop and deploy data pipelines, workflows, and automated processes especially geospatial and remote sensing based
Partner closely with study investigators and staff to identify high-impact data applications and support effective decision-making
Apply data science best practices to test, deploy, and iterate on analytic solutions
Perform data manipulation, cleaning, and quality assurance to ensure data integrity
Monitor project progress, track activities, and provide regular updates to PI and study team members on status and deliverables
Draft reports, figures, and presentations summarizing analytic methodology and findings
Maintain currency with new tools and methods in geospatial and data science, applying up-to-date techniques to ongoing research
Maintain technical documentation and support continuous process improvement