Machine Learning Postdoctoral Fellow

at  Lawrence Berkeley National Laboratory

Lawrence Berkeley National Lab’s (LBNL) Energy Storage & Distributed Resources Division has an opening for a Machine Learning Postdoctoral Fellow to join the team.
The Center for Ionomer-based Water Electrolysis (CIWE), an Energy Earthshot Research Center, has an immediate opening for a postdoctoral researcher to conduct applied research in the area of machine learning, pattern/feature detection, statistical description, computer vision, image processing and analysis, and parallel computing and will also be part of the Math for Experimental Data Analysis Group. The overall objectives for this work are to develop new software tools that enable scientific knowledge discovery using high performance computational platforms and advance the state-of-the-art in data-intensive analysis. You will be part of an experienced team conducting R&D in the areas of data-intensive ML, high performance, visualization, analysis, and data management. You will be working as part of a multidisciplinary team composed of computer, computational, mathematics and experimental scientists engaged in areas like material design, granulometry, structural analysis, earth sciences, photovoltaic materials, batteries, chip design, being all these areas approached through computer vision and/or machine learning applied to micrographies.
As a part of CIWE, there will be a focus on the fundamental challenges of water electrolysis and exploring the catalyst-ionomer interface, while being guided by the DOE’s Hydrogen Shot Goal of $1/kg in one decade. This center is a collaborative environment, where you will be engaging with scientists from various fields, spanning material synthesis and diagnostics, advanced characterization, electromechanochemistry, modeling, theory, and data science fields. The multidisciplinary and multi-investigator team is an exciting opportunity to grow your network, get exposed to different techniques and methodologies, and learn from some of the best researchers at Berkeley Lab.

DESIRED QUALIFICATIONS:

• Knowledge of one or more of the following science areas: micro-tomography, SEM, TEM, STEM, multimodal imaging.
• Software engineering tools experience: make, cmake, revision control systems (CVS, SVN, git), gdb.
• Demonstrated ability to design and implement image processing/statistical analysis software, preferably shared and distributed memory parallel software, in one or more of the following programming languages and parallel libraries/languages/environments: Python, C/C++, Java, R, MPI, OpenMP, CUDA.
• Experience with the DASK library.
• Prior work experience designing and implementing image processing/analysis software.
• Any knowledge of the following areas: water electrolysis, electrochemical systems, hydrogen technologies
• Familiarity with scientific data models/formats and I/O libraries, as well as engines for large-scale data processing, e.g. Apache Spark.

WHAT YOU WILL DO:

• Develop theory and optimization techniques for tackling noise and missing data for improved image resolution.
• Design and implement parallel algorithms in computer vision and machine learning applied to DOE image-based data.
• Develop new data-driven methods that leverage physics-informed machine learning for semantic segmentation and generative modeling of porous media and material interfaces.
• Develop software tools involving data-intensive computing, analytics and machine learning, enforcing reproducibility (e.g. Doxygen, git).
• Publish and present research results in journals and conferences.
• Maintain documentation of theory, derivations, and results.
• Adhere with the Berkeley Lab and ETA safety requirements.
• Work on meeting milestones and reporting them to DOE, various consortia leadership, and industrial sponsors.
• Collaborate and work with a team of researchers from diverse backgrounds, and interface with research teams across industry, academia, and national laboratories.

ADDITIONAL RESPONSIBILITIES AS NEEDED:

• Prepare results, figures, and write-ups for research/grant proposals.
• Participate in professional society activities.