Leads development of standards and validation frameworks for dynamic structural biology data, focusing on ensemble models from X-ray crystallography and cryo-EM. Collaborates with engineers to build deposition, search, and retrieval infrastructure for the diffUSE Project. Requires PhD in structural biology or related field.
100k – 180k/yr
On-siteData Science
About the role
Key Responsibilities
Oversee development of ensemble-aware validation frameworks that assess fit-to-data, physical realism, and uncertainty across diverse structural representations
Identify and prioritize technical challenges, from data representation to validation frameworks
Guide the creation of data deposition, search, and retrieval tools that allow users to interrogate and interpret structural heterogeneity at scale
Help coordinate with stakeholders to ensure interoperability and adoption
Work with software developers, data engineers, and user experience designers to translate scientific requirements into robust technical solutions
Required Skills and Qualifications
Ph.D. in structural biology, biophysics, computational biology, or related field
Demonstrated expertise in structural biology methods
Deep understanding of structural heterogeneity and dynamics in biomolecular systems
Experience with data standards, metadata frameworks, or scientific database development
Strong collaborative skills and ability to build consensus across diverse scientific communities
Preferred Skills and Experience
Experience with PDB, EMDB, BMRB, or other structural biology databases
Knowledge of validation methods for experimental and computational structural data
Familiarity with machine learning workflows and ML-ready data formats
Background in model uncertainty quantification or ensemble refinement methods
Understanding of software development practices and data engineering principles
Track record of working at the interface of methods development and infrastructure
Data Scientist embedded across Product, Finance, Marketing, and Platform teams to build models, design experiments, develop data pipelines, and drive strategic insights using Python, SQL, and distributed systems. Requires 4+ years experience and cross-functional collaboration.
100k – 250k/yr
On-site4+ YOEData Science
Data Scientist
PinterestSan Francisco, CA +1
As a Data Scientist, you will shape the future of Pinterest's products by applying quantitative modeling, experimentation, and algorithms to complex engineering challenges. You will collaborate with cross-functional partners to bring scientific rigor to product development and deliver insights that influence product teams.
101k – 209k/yr
Remote4+ YOEData Science
Data Scientist, Growth Product
ChimeSan Francisco, CA
Growth Product Scientist partnering with PMs, engineers, and marketers to drive acquisition, activation, and retention through experimentation, causal analysis, and self-serve analytics tooling.
109k – 150k/yr
Hybrid3+ YOEData Science
Data Science Fellow - AI/NLP
AxleUnited States
Postdoctoral researcher developing AI/NLP and knowledge engineering methods to transform biomedical literature into structured, evidence-grounded knowledge for organoid protocol standardization. Requires PhD and strong Python/NLP research experience.
90k – 100k/yr
RemoteData Science
Bioinformatics Scientist
AxleBethesda, MD
Develops and maintains bioinformatics pipelines for NGS data analysis including variant calling, gene expression, and genomics assembly. Provides statistical modeling, scripting support, and experimental design consulting for NIAID researchers; requires 4+ years experience and expertise in Python/R and pipeline frameworks.