Summary of Position
This Data Scientist will help develop, deploy, maintain, and effectively use tools for the analysis of all-optical electrophysiology data, as well as data from other cellular neuroscience techniques (e.g. high-content imaging, neurite tracing, gene and protein expression experiments). They will work as part of a small, close-knit team at the hub of scientific programs to find novel therapeutics for rare genetic diseases. The ideal candidate will be a thoughtful and creative programmer excited to distill their expertise into automated pipelines and cutting-edge machine learning programs and is eager to gain practical experience across all stages of the software lifecycle. We are looking for somebody motivated to ask lots of questions and learn expansively across a wide array of skills and problem domains. This role will have a special emphasis manifold learning, deep neural network models, visualization, explainable AI techniques, software architecture and design, image processing, and developing novel algorithms for neighborhood search.
Quiver Bioscience is a technology-driven company established to create transformational medicines for the brain. We combine proprietary single-cell functional assays with other multi-modal measurements to discover new biology and new drug targets. We take advantage of cutting-edge AI/ML to build the world’s most information-rich maps of neuronal function to drive our drug discovery programs.
Remote applicants considered.
Responsibilities and Duties
- Analyze electrophysiological (and other biological) data to serve research project goals. Make effective visualizations, draw sound inferences from complex experiments, assist biologists with experimental design and implementation, conduct reproducible analyses, and disseminate analytics findings with biologists and other stakeholders.
- Help develop professional-grade tools for learning, visualizing, explaining, and utilizing manifolds embedded within high-dimensional data. Help deploy methods for jointly embedding multi-modality data.
- Contribute to all aspects of analytics software development including design, implementation, source control, performance optimization, unit testing, defect management, documentation, and ongoing maintenance and support.
- Improve the accessibility and interpretability of our internal analysis tools by creating apps, user interfaces, visualization tools, automated pipelines, and cloud compute back-ends.
- Proficiently manage timelines, relationships, and work priorities to comfortably operate independently in order to make an impact.
- Utilize excellent interpersonal skills to build consensus, share insights with relevant stakeholders, deliver interpretable data products, and serve both business and scientific goals of the company with your work.
Minimum Qualifications Required
- MS degree (PhD desirable) or corresponding demonstrable professional experience in Data Science, Computer Science, Math, (Bio)Statistics, Physics, or related technical discipline (e.g., engineering, science, or biology with a strong quantitative flavor), with a track record suitable for a senior role.
- Comfort with multiple programming languages and computational APIs (the role will utilize Python, Matlab, R, git, SQL, and AWS, among others).
- Experience developing complex data pipelines or analysis tools.
- Deep understanding of manifold learning and unsupervised techniques.
- Broad experience with commonly used data science and machine learning toolkits, libraries, and frameworks (sklearm, pytorch, statsmodels etc). Some experience developing interactive APIs (e.g. Flask, Shiny, Qt)
- High level of creativity, with a passion for neuroscience or the science of rare genetic diseases.
- Excellent skills in the areas of verbal/written communication, problem solving, and leadership.
Additional Qualifications Desired
- Knowledge and experience in biophysics, physiology, or neuroscience, especially electrophysiology, high-content imaging, or neurite tracing. Familiarity with drug development or rare genetic disease research is a plus.
- Comfortable with linear algebra and probability theory.
- Experience with statistical analysis and techniques for inference (including regression, splines/smooths, bootstrap and permutation methods, power analysis, theory of experimental design etc).
- Experience with deep-learning and neural network models, including modern convolutional models, autoencoders, variational techniques, joint embeddings, data augmentation, and current best-practices for training and optimization.
- Experience with image processing, video processing, signal processing, or time series analysis.
- Experience with “explainable AI” techniques, with an emphasis on helping the team reason about internal states, visualize information flows, detect out-of-domain data, and develop adversarial samples to help define robustness boundaries.