Los Alamos, NM30+ days ago
The research will involve the design, implementation, and evaluation of advanced computational algorithms that: Identify spatial and compositional patterns in multi-element mapping datasets (e.g., gradients, segregation, inclusions, clustering, interfaces, and anomalous regions); Recommend follow-on measurement actions to maximize information gain, including: Identifying regions where additional raster scans should be performed, Suggesting locations for higher-resolution or higher-statistics scans, Proposing targeted point analyses to refine compositional estimates; Optimize acquisition parameters (e.g., dwell time, step size, spatial resolution, and count-statistics proxies) to enhance data quality while respecting operational and instrument constraints; Detect and manage out-of-bounds or invalid parameter selections by incorporating safe operating limits into the decision-making framework; Integrate uncertainty quantification and data-quality metrics to prioritize measurements and avoid low-value or unreliable regions. Strong programming experience in Python, including scientific computing libraries (NumPy, SciPy, scikit-learn, PyTorch/TensorFlow, etc.); Experience with machine learning, AI methods, or data-driven modeling; Familiarity with uncertainty quantification, statistical inference, or Bayesian experimental design; Experience analyzing spatially resolved or imaging datasets; Demonstrated ability to design and implement modular, reproducible scientific software; Experience working with scientific instrumentation data or experimental workflows (preferred); Demonstrated ability to conduct independent and collaborative research; Strong written and oral communication skills.