Scientific Software Engineer - AI/ML for Hyperspectral Imaging
About The Position
Lawrence Berkeley National Laboratory’s (Berkeley Lab) Advanced Light Source (ALS) Division has an opening for a Scientific Software Engineer specializing in AI/ML for hyperspectral imaging. This role advances AI-driven scientific discovery by developing machine learning methods and scalable data analysis tools for complex, high-dimensional scientific datasets. The engineer will build and generalize segmentation, feature extraction, and modeling workflows, including development of a foundation model to extract scientific information from hyperspectral imaging data across infrared imaging, resonant soft X-ray scattering, tomography, and ptychography. The Advanced Light Source is a U.S. Department of Energy (DOE) Office of Science national scientific user facility that produces exceptionally bright soft and hard x-ray, ultraviolet, and infrared light. With a strong scientific reputation, expert staff, and advanced capabilities, the ALS attracts thousands of academic and industrial users each year in condensed matter and quantum materials, energy sciences, biosciences, earth and planetary sciences and more. The ALS is one of five Berkeley Lab user facilities that serve 15,000 users annually. Co-located with the Molecular Foundry, NERSC supercomputing center, and Berkeley Lab's materials, chemical sciences, biosciences, and other divisions, it provides an ideal collaborative environment for innovative scientific discoveries. The ALS is a global leader in soft x-ray science, and aims to maintain its leadership with ALS-U, a major project to upgrade the facility to a fourth-generation light source. This upgrade will position the facility among the brightest soft x-ray light sources in the world, offering capabilities that no other facility can provide.
Requirements
- Bachelor’s degree and a minimum of 2 years of related experience; or an advanced degree without experience (Master’s or PhD); or equivalent years of work experience.
- Experience with the open-source scientific Python ecosystem (e.g., NumPy, PyTorch, TensorFlow, scikit-learn).
- Hands-on experience analyzing complex scientific datasets, including imaging, multivariate, multimodal, multichannel, or volumetric data.
- Hands-on experience developing, training, or applying AI/ML models, including segmentation methods, for scientific data analysis.
- Experience developing or contributing to software projects, including collaborative or open-source development.
- Experience building or maintaining data analysis pipelines or scientific workflows.
- Ability to work collaboratively with a team of scientists and engineers.
- Knowledge of AI/ML principles and data analysis methods relevant to complex scientific data, including segmentation, feature extraction, model training, validation, and interpretation.
- Knowledge of GPU acceleration and performance profiling for large scale workflows
- Demonstrated ability to design and evaluate workflows for processing, analyzing, and representing complex scientific imaging and high-dimensional data.
- Proficiency to validate data quality, model outputs, and workflow results against technical and scientific expectations.
- Proven capability to develop, test, debug, document, and maintain reproducible software and machine learning workflows.
- Effectiveness in communicating technical results clearly, both in writing and verbally, to interdisciplinary audiences.
- Flexibility and capacity to learn new scientific domains, data modalities, tools, and computational techniques within evolving project timelines.
Nice To Haves
- Experience with hyperspectral scientific datasets.
- Experience with High-Performance Computing (HPC) environments.
- Experience with MLOps tools such as MLflow.
- Experience with CI/CD tools (e.g., GitHub Actions).
- Familiarity with hyperspectral imaging data.
- Familiarity with agent-based or AI orchestration frameworks (e.g., LLM-based or multi-agent systems).
Responsibilities
- Expand and generalize AI-driven segmentation and feature extraction workflows across multiple scientific modalities and domains.
- With general guidance, develop and apply specialized machine learning models for hyperspectral imaging data, serving as a key target domain for high-dimensional spectral–spatial analysis.
- Operating under broad direction, develop interfaces and data products that enable machine learning models to be integrated into higher-level automation and agent-based systems.
- Implement scalable pipelines that transform experimental data into structured, semantically meaningful scientific representations.
- Ensure reproducibility, traceability, and interoperability of software and AI workflows across systems and facilities.
- Collaborate with scientists and engineers to gather requirements, validate results, and translate scientific needs into software solutions.
- Design, test, deploy, and maintain robust software using modern development practices (e.g., CI/CD, version control, unit testing).
- Contribute to open-source projects, develop documentation, provide user support, and communicate work through presentations.
Benefits
- Full-time 2 year, term appointment with the possibility of extension or conversion to Career appointment
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
