DescriptionWFIRM is a multidisciplinary group of physicians and research scientist involved in a myriad of programs focused on bringing curative medicines to the patient. In addition to our world class regenerative medical programs, WFIRM is recognized as a leader in the organ-on-a-chip platform as well as pushing the boundaries of tissue engineering. Through its relationship with Virginia Tech School of Biomedical Engineering and Sciences, WFIRM is involved in developing solutions over the entire spectrum of regenerative medicine. In short, WFIRM is an unique environment ripe with opportunities for applying AI/ML across a diverse set of scientific disciplines.
Successful candidates will be responsible for some or all of the following:
- Design, develop, and validate new machine learning models that can uncover and describe the relationship between genetic and genomic variation, cellular phenotypes, and clinical conditions and symptoms.
- Design, develop, and validate new methods for characterizing variation in large cellular populations assayed in high-throughput, multi-dimensional assays.
- Design and integrate new computational methods, mathematical models, and bioinformatics approaches with molecular assays at the bench to provide mechanistic understandings of development and regeneration, discover therapies, and streamline the application of systems and synthetic biology.
- Develop computational approaches rooted in machine learning to make precise biological inferences that can not only guide experiments, but also reveal general mechanistic principles underlying cellular organization and molecular networks.
- Work in a highly collaborative and cross-disciplinary team to advance technology platforms aimed at delivering robust, quantitative, mechanistic, and scalable research and clinical benefit.
- Developing methodologies to leverage R&D data and artificial intelligence to connect different components; patients, tissues, in vitro models and in vivo models, in translational research.
- Develop, implement, and validate the application and use of modern machine learning and artificial intelligence techniques – applying robust statistical and quantitative methods for the design of experiments – to allow rigorous model evaluation, uncertainty quantification, prediction, and data generation.
- Integrate advances in diverse fields of machine learning and computer science into modern analytics infrastructure and workflows.
Essential Education and Expertise:
- Ph.D. in Computer Science, Applied Mathematics, Engineering, Computational Chemistry, Computational Biology, Physics or related field with a focus in Machine Learning or Artificial Intelligence
- Expertise demonstrated by research publications or industrial experience in modern, applied machine learning, data mining, pattern recognition, or artificial intelligence. Direct experience with and application to the analysis of complex biological datasets and phenomena is ideal.
- Excellent communication skills are a must
- Ability to comfortably interact with diverse group of scientists and physicians
- Practical and theoretical understanding of fundamental models and algorithms in supervised and unsupervised learning: generalized linear models, kernel machines, decision trees, neural networks; boosting and model aggregation; clustering and mixture modeling; Bayesian inference and model selection, variational inference, Gaussian processes, causal inference, Monte Carlo methods; dimensionality reduction and manifold learning
- Competency in programming and scripting required utilizing languages such as C/C++ and Python.
WFUSOM-1