Data Scientist

University of California, San Francisco; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

University of California, San Francisco is seeking a Bioinformatics Programmer/Data Scientist to develop and maintain pipelines for large-scale medical data analysis. You will implement pipelines in R, Python, Go, Rust, shell, SQL, WDL and use tools like Docker, with cloud and on-premises compute.

You will work under the PI, perform bioinformatic analyses including variant calling and annotation, contribute to manuscripts, and help lead authorship teams while learning new techniques across cloud

Qualifications

• Bachelor's degree in biological science, computational/programming, or related area.
• 12+ months of demonstrated work experience using medical or health-related data, including ETL pipelines and data analysis.
• Working knowledge of bioinformatics methods and data structures.
• Working knowledge of biostatistics and basic statistical testing.
• Working knowledge of systems programming and databases.
• Ability to manage time and meet deadlines on assigned parts of projects.
• Fluency with R or Python for statistical programming.

Responsibilities

• Design, develop, debug, and utilize programs to extract, transform, and load data for analysis.
• Develop data pipelines to standardize and automate data processing steps.
• Build and run programs to extract imaging, biosignals, and medical data from clinical systems.
• Perform data quality control and statistical analyses.
• Manage cloud and containerized environments (Docker, cloud platforms).
• Write documentation and comments for analyses, code, and pipelines.
• Contribute to manuscript preparation and dissemination of results.

Skills

Python

R

Go

Rust

SQL

WDL

shell

Education

Bachelor's degree

Tools

AWS

Azure

GCP

plink2

Git

Job description

Job Function Summary

Involves developing and utilizing computational tools and systems to analyze and interpret biological or other research data. Utilizes and develops algorithms, computational techniques, and standard statistical methodologies. Helps in the design of new experiments and leads the execution of building machine learning and statistical models. Implements end‑user needs in database development, maintenance, searching, and integration. Maintains computational infrastructure and manages and tracks the flow of samples and information for large‑scale studies. Provides bioinformatics and access to public and proprietary databases. Manages cloud and on‑premises computational infrastructure and data.

Job Description

Our research efforts are at the intersection of cardiovascular disease and human genetics. Our clinical research employs new techniques for deep phenotyping, such as deep learning. These techniques rely on a solid foundation of classical bioinformatics. The Bioinformatics Programmer/Data Scientist will assist in managing, cleaning, and analyzing large‑scale medical data using a wide variety of analytic techniques, both in the cloud and with on‑premises compute depending on data permissions. Experience with a cloud provider such as AWS, Microsoft Azure, or Google Cloud is a plus, and ability to learn how to manage cloud‑based pipelines and to perform cloud data management will be essential skills to develop and maintain. Maintaining bioinformatic databases by obtaining and restructuring data, including both UCSF proprietary data and public data, and writing tools to streamline discovery and replication analyses using these databases will be core responsibilities. An important task will be writing and maintaining analytic pipelines in languages such as R, Python, Go, Rust, shell, SQL, WDL, and/or other appropriate languages, and using tools such as Docker. Experience with databases or the ability to learn will be requisite. Under the supervision of the PI, the Data Scientist will also be involved in data analysis, and will be comfortable with bioinformatic analyses including variant calling and annotation. There will be opportunities to employ cutting‑edge methods and to develop new methods. The ability to learn and implement new techniques depending on the problem at hand will be an essential skill, thus requiring a strong foundation in computer programming. This position will also include administrative duties and will have the opportunity to participate in—and to lead—authorship teams.

Responsibilities

• Design, develop, debug and utilize computer programs necessary to extract, transform, and load data and prepare it for analysis.
• Assist in extracting, transforming, and loading data from clinical sources and research sources using a wide variety of analytic techniques.
• Develop data pipelines to standardize and automate repeatable data processing steps as appropriate.
• Build and run programs to extract relevant imaging, biosignals, and medical data from clinical systems, including UCSF data.
• Perform data quality control.
• Use software such as plink2 to manage, merge, split, and analyze sequencing and genetic imputation data.
• Perform quality control at the sample-, variant-, and genotype-level for genetic sequencing and imputation data.
• Conduct analyses with linear, logistic, or survival models where appropriate.
• Assist with management of research databases and shared computational resources.
• Manage cloud virtual environments and containerization with tools such as Docker.
• Assist with report preparation and analysis for internal constituents and scientific publication and dissemination; describe methods, results and implications of the work.
• Generate appropriate data visualizations.
• Assist with general manuscript preparation and submission.
• Write internal‑facing documentation for all analyses, coding, tooling, and pipelines, clearly describing what is done and why.
• Write appropriate code comments explaining unintuitive decisions, algorithms, and functions.
• Use change‑management software, including git for code management.
• Proactively communicate to the PI about barriers to progress and possible code or workflow improvements.
• Provide the PI and collaborators with recommendations and guidance for subsequent steps.

Qualifications

Required Qualifications

• Bachelor's degree in biological science, computational/programming, or related area and/or equivalent experience/training.
• 12 months or more of demonstrated work experience using medical and/or health‑related data, including developing pipelines for extracting, transforming, and loading data, and data analysis.
• Working knowledge of bioinformatics methods and data structures.
• Working knowledge of biostatistics and basic statistical testing.
• Working knowledge of systems programming and databases.
• Working knowledge of application and data security concepts.
• Ability to effectively manage time and see assigned parts of projects through to completion on deadline.
• Basic consultation and communication skills.
• Demonstrated fluency and competency with statistical programming with the R programming language or the Python programming language.
• Experience with or a demonstrated ability to learn and implement data management and computational pipelines for management of large‑scale data.
• At least 6 months of experience in direct data management and analysis using medical and/or health‑related data using the above tools.
• Ability to lead and maintain data pipelines for real‑time data acquisition from clinical systems.
• Ability to multi‑task and work well with limited supervision.
• Working project management skills.
• Interpersonal skills in order to work with both technical and non‑technical personnel at various levels in the organization.
• Ability to communicate technical information in a clear and concise manner.
• Self‑motivated, able to learn quickly, meet deadlines and demonstrate problem‑solving skills.

Preferred Qualifications

• MS or greater in a related science or an equivalent combination of education and experience.
• PhD in a field relevant to biomedical research (bioinformatics, biomedical engineering), or computer science, machine learning, artificial intelligence, or similar.