Bioinformatics Programmer 5

UCSF Health, AG; San Francisco (CA); Sur place; USD 180 000 - 240 000; Plein temps

Résumé du poste

UCSF, through the Quantitative Biosciences Institute (QBI) in San Francisco, seeks a senior computational leader to advance AI/machine learning, structural biology, and systems biology across multiple research programs.

You will shape computational strategy, build reusable methods, and provide mentorship to scientists and staff while collaborating with international partners to translate large biomedical data into actionable insights.

Qualifications

• Bachelor's degree in biological science, computational / programming, or related area.
• Expert knowledge of structural bioinformatics and protein-protein interaction analysis.
• Minimum of ten years of experience designing computational methods for biological research.
• Expert knowledge of AI/ML methods applied to biology, including deep-learning protein structure prediction.
• Expert knowledge of modern biology including structural biology, proteomics, and genomics.
• Ability to interpret experimental readouts and translate predictions into hypotheses.
• Ability to lead across multi-year, multi-investigator programs with multiple UCSF units.
• Strong interpersonal skills and ability to communicate technical information clearly.
• Ability to interface with management on a regular basis.
• Experience providing authoritative technical consultation to senior investigators.
• Knowledge of cloud platforms, containerization, and version control.
• Knowledge of research data governance and data management practices.

Responsabilités

• Functions as a recognized expert in computational bioinformatics, AI/machine learning, and structural biology.
• Develops and directs advanced computational approaches used across multiple major QBI research programs and collaborations.
• Applies expert knowledge to complex problems in protein-protein interaction prediction, structural modeling, and large-scale data integration.
• Provides computational leadership across multi-investigator programs involving UCSF units and external collaborators.
• Shapes computational strategy, establishes standards and reproducibility practices, and develops reusable resources.
• Represents QBI and UCSF computation through publications, presentations, and shared resources.
• Provides technical direction and mentorship to computational staff, postdocs, and students.

Connaissances

Python

AI in biology

Protein structure

LLM usage

Leadership

Cloud platforms

Containerization

Version control

Graph neural networks

Formation

Bachelor's degree in biological science

PhD in biophysics / computational biology

Outils

Containerization

Description du poste

Job Summary

The Quantitative Biosciences Institute (QBI) at UCSF brings together researchers across the biomedical, physical, and computational sciences to address complex problems in biology and human disease. QBI supports large, multi-investigator programs that integrate quantitative proteomics, structural biology, genetics, and advanced computational and AI methods, and works extensively with academic, government, and industry partners in the United States and internationally. Based at Byers Hall on the UCSF Mission Bay campus, QBI provides a highly collaborative, interdisciplinary environment in which computational scientists work directly alongside experimental groups to translate large-scale biological data into mechanistic understanding and therapeutic hypotheses.

Job Description

The Quantitative Biosciences Institute (QBI) at UCSF brings together researchers across the biomedical, physical, and computational sciences to address complex problems in biology and human disease. QBI supports large, multi-investigator programs that integrate quantitative proteomics, structural biology, genetics, and advanced computational and AI methods, and works extensively with academic, government, and industry partners in the United States and internationally. Based at Byers Hall on the UCSF Mission Bay campus, QBI provides a highly collaborative, interdisciplinary environment in which computational scientists work directly alongside experimental groups to translate large-scale biological data into mechanistic understanding and therapeutic hypotheses.

Custom Scope

Functions as a recognized expert in computational bioinformatics, AI/machine learning, and structural biology, with responsibility for developing and directing advanced computational approaches used across multiple major QBI research programs and collaborations. Applies expert knowledge to highly complex, novel problems in protein-protein interaction prediction, structural modeling, scientific AI, and large-scale biological data integration where established approaches may be inadequate or nonexistent.

Provides computational leadership across multi-investigator research programs involving researchers from multiple UCSF schools, departments, and research centers, as well as domestic and international academic institutions and other external collaborators. Current work supports major QBI collaborative initiatives, including the ARIA-funded autism program and research collaborations involving institutions such as Gladstone Institutes, NYU Langone Health, Johns Hopkins University, and the Icahn School of Medicine at Mount Sinai, as well as research supported through federal programs including NIH and DARPA.

Serves as a senior technical authority who shapes computational strategy, establishes and advances technical standards and reproducibility practices, develops computational methods and resources intended for reuse across research teams, and provides authoritative consultation to scientists and computational professionals. Represents QBI and UCSF computational expertise through collaborative publications, presentations, methods, and resources shared internally and externally. Provides technical direction and mentorship to computational staff, postdoctoral researchers, and students.

Qualifications

Required Qualifications

• Bachelor's degree in biological science, computational / programming, or related area and / or equivalent experience / training.
• Expert knowledge of structural bioinformatics and protein-protein interaction analysis, including the computational methods and data structures used to represent protein structures and interaction networks.
• Minimum of ten years of experience designing and implementing computational methods for biological research, with expert-level proficiency in Python for scientific computing.
• Expert knowledge of AI/ML methods applied to biology, including deep-learning protein structure prediction and applied use of LLM-based tools.
• Expert knowledge of modern biology and the applicable field of research, including structural biology, quantitative proteomics, functional genomics, and their underlying experimental methods.
• Demonstrated ability to work with experimental researchers to interpret experimental readouts, translate computational predictions into testable hypotheses, and contribute to experimental design.
• Demonstrated ability to provide computational leadership across multi-year, multi-investigator research programs involving multiple UCSF units and external collaborating institutions.
• Highly developed interpersonal skills and ability to communicate technical information clearly to technical and non-technical personnel at all levels internally and externally.
• Highly developed ability to interface with management on a regular basis.
• Demonstrated ability to provide authoritative technical consultation to senior scientific investigators and research leaders on complex computational strategy, methodology, and interpretation.
• Working knowledge of computational infrastructure and reproducible development practices, including cloud platforms, containerization, and version control.
• Working knowledge of research data governance, data security, and scientific data management practices.

Preferred Qualifications

• Ph.D. in biophysics, computational biology, bioinformatics, structural biology, or a related field.
• Demonstrated external recognition as a subject matter expert, such as first-author publications in leading journals and invited presentations at international scientific meetings.
• Experience designing, building, and evaluating LLM-based agents and agentic workflows for scientific applications, including retrieval-augmented analysis and systematic evaluation.
• Experience applying computational methods in drug discovery or translational research, including target identification and mechanism-of-action analysis.
• Experience mentoring or providing technical direction to scientific staff, postdoctoral fellows, and students.
• Experience with graph neural networks or other deep-learning approaches applied to biological networks