Apply on Employer Site

Fred Hutch · 9 hours ago

Data Scientist II

Seattle, WA

Full-time

Onsite

Mid, Senior Level

$104K/yr - $165K/yr

5+ years exp

Fred Hutchinson Cancer Center is an independent, nonprofit organization focused on cancer and infectious diseases. The Data Scientist II will provide analytic support for the Biostatistics, Bioinformatics, and Epidemiology Program, leveraging statistical modeling techniques to analyze data and develop epidemic models for HIV preventive interventions.

Hospital & Health Care

No H1B

Responsibilities

Develop and refine mechanistic mathematical models to study the effectiveness and efficiency of individual and combined interventions for HIV prevention

Develop a modeling framework to process and analyze epidemiological data from multiple sources (clinical and observational studies, demonstration projects) to parameterize and calibrate complex epidemic models

Develop novel statistical and mathematical modeling approaches for integration of complex data sets as model inputs

Build open-source, reusable scripts

Communicate results from modeling analyses to technical and non-technical audiences

Collaborate with and advise team members, including post-docs, statistical research associates, bioinformaticians, staff scientists

Lead and contribute to manuscripts and presentations on novel computational approaches for evaluation of HIV preventive programs and interventions

Other duties as assigned

Qualification

Machine LearningStatistical ModelingData AnalysisR ProgrammingPythonCloud ComputingAgile MethodologyCollaborationCommunication SkillsCritical Thinking

Required

A Bachelor's degree or higher in computer science, data science, statistics, informatics, or equivalent

Core competency in at least one of the following: genomics, natural language, image processing, medical records or claims

Experience in software development in the context of machine learning, such as R/Python, Weka, or others

A sound understanding of software development best practices (e.g., version control, unit testing, regression testing)

A fundamental understanding of machine learning, both supervised and unsupervised, and experience with machine learning tools and applications

A strong background in both formal statistics and predictive analytics, and some experience with the analytic process

Software development in the context of machine learning, ideally in R or Python

Experience with working in a cloud environment (e.g., Amazon's EC2)

Experience working with an agile development methodology

Knowledge of best practices in data analysis and scientific computing (e.g., literate programming, reproducible research)

Experience with using and managing data in clinically regulated environments

Preferred

PhD degree in Statistics, Mathematics, Biostatistics, Computer Science, Physics or equivalent

Experience in mathematical modeling of biological systems, including but not limited to modeling infectious disease transmission and population dynamics

5 year of hands-on experience of data analyses

Proficiency in common object-oriented programming language (e.g. Java, C++, C#), desired

Demonstrated proficiency with Bayesian statistical methods of model calibration

Experience with large network models is desired

Demonstrated rigor and reproducibility through well organized and well documented code and/or committed to a public code repository (e.g. Github)

A strong interest in exploring complex and epidemiological data sets to uncover embedded relationships

A strong interest in advancing HIV prevention and vaccine research

Highest scientific rigor and integrity

Dedication to open and reproducible research

Ability to work autonomously and collaboratively within multidisciplinary teams including statisticians, mathematical modelers, statistical research associates and programmers, clinical scientists, etc

Strong oral and written communication and critical thinking skills are a must for this position

Experience applying machine learning algorithms (e.g., neural networks), predictive models, and classification methods