Senior Data Scientist

Character Biosciences is a drug discovery and development company building a world-class platform for deeply-phenotyped databases that integrate genomics with longitudinal clinical and imaging data. Our interdisciplinary team, comprising experts in clinical science, data science, statistical genetics, machine learning and drug discovery, utilizes this platform to determine genetic drivers of disease progression, advance novel therapeutics and define genetics-based patient stratification. Powered by our data platform, Character Bio is currently advancing two programs in Dry Age-related Macular Degeneration with additional programs for other disease areas (e.g. Glaucoma) in earlier stages of discovery research.

As a Data Scientist, you will be responsible for thinking critically about how we can best use our unique, longitudinal, real-world dataset to power our drug discovery platform. You will design and build models for new digital biomarkers, and you will optimize these biomarkers for use in target discovery and clinical trial design. You will also push the boundary for how we use these biomarkers to derive clinical endpoints, measure disease progression, and stratify our patient population. You will also integrate these models, analyses, and visualizations into our data platform for use by our Clinical and Science teams. This role is crucial to advancing how we utilize our unique data platform to drive scientific and clinical discoveries.

Key Responsibilities:

• In collaboration with our Data Science (DS), Clinical, and Genetics teams, develop and qualify clinical endpoints, models of disease progression, and patient stratification criteria using our unique longitudinal real world data.
• Implement new methods and models to support clinical trial design, including strategies for patient targeting, stratification, and inclusion and endpoint optimization
• Design and build new digital biomarkers and longitudinal phenotypes aligned with our clinical endpoints to power our target discovery platform
• Build data science products (dashboards, pipelines, models, etc.) to catalyze the discovery efforts of our Science and Clinical teams
  
  

Skills and Qualifications:

• PhD (or Masters with 4 years of experience) in Bioinformatics, Biostatistics, Computer Science, or related technical field with 2 years of experience
• Proven track record of owning and leading projects through the data science life cycle from initial problem through data processing to analysis and modeling and finally operationalizing your solution
• Strong proficiency in python and modern data science frameworks (pandas, sci-kit, PyTorch, Tensorflow, etc.), and prior experience with other programming languages such as bash and R
• Deep knowledge of statistical methods (experimental design, GLMs, mixed models, dimension reduction, imputation, etc.) and machine learning models (random forest, SVM, and modern deep learning models)
• Experience developing longitudinal models on biomedical data, particularly real world data including electronic medical records (EMRs)
• Experience developing and using computer vision models (e.g. CNNs) for biomedical data
• Strong problem-solving skills, with a focus on using data to drive action and decision making
• Excellent communication skills, with the ability to work cross-functionally in a team-oriented environment.
  
  

Preferred Qualifications:

• Experience with clinical trial design and biomarker development
• Experience with ophthalmology data, particularly segmentation models and clinical endpoints
• Experience with genetics data and analyses (association testing, functional genomics, etc.)