Computational Postdoctoral Fellow (Optimization and Learning for Imaging) | Berkeley, California, United States | Lawrence Berkeley National Laboratory

Position:	Computational Postdoctoral Fellow (Optimization and Learning for Imaging)
Institution:	Lawrence Berkeley National Laboratory
Location:	Berkeley, California, United States
Duties:	Develop theory and optimization techniques for tackling noise and missing data for improved subtomogram resolution; Develop algorithms for automated marker-less alignment of X-ray and electron tomography data; Develop new data-driven methods that leverage physics-informed machine learning for reconstructing non-rigid deformations and generative modeling of conformational heterogeneity in electron tomography; Apply these new algorithms to enable high-resolution 3D reconstructions of biomolecules from cellular tomographic data; Publish scientific papers in high-impact journals and present findings at seminars and conferences; Maintain documentation of theory, derivations, and results
Requirements:	A recent Ph.D. (within the last 1-2 years) in Applied Mathematics, Computational Biophysics/Physics, Computer Science, Data Science or a related discipline; Experience developing numerical methods for solving inverse problems in imaging including but not limited to phase retrieval, iterative reconstruction for tomography, and regularization techniques; Experience with generative models, variational inference, and physics informed machine learning; Strong background in scientific computing including coding experience in C++, Fortran, and Python; Knowledge of physics and mathematics of X-ray and electron microscopy

Text:	Computational Postdoctoral Fellow (Optimization and Learning for Imaging) Develop theory and optimization techniques for tackling noise and missing data for improved subtomogram resolution; Develop algorithms for automated marker-less alignment of X-ray and electron tomography data; Develop new data-driven methods that leverage physics-informed machine learning for reconstructing non-rigid deformations and generative modeling of conformational heterogeneity in electron tomography; Apply these new algorithms to enable high-resolution 3D reconstructions of biomolecules from cellular tomographic data; Publish scientific papers in high-impact journals and present findings at seminars and conferences; Maintain documentation of theory, derivations, and results A recent Ph.D. (within the last 1-2 years) in Applied Mathematics, Computational Biophysics/Physics, Computer Science, Data Science or a related discipline; Experience developing numerical methods for solving inverse problems in imaging including but not limited to phase retrieval, iterative reconstruction for tomography, and regularization techniques; Experience with generative models, variational inference, and physics informed machine learning; Strong background in scientific computing including coding experience in C++, Fortran, and Python; Knowledge of physics and mathematics of X-ray and electron microscopy