Ames National Laboratory Scientist I
Core
Architect digital frameworks (graph neural networks, molecular representations, thermodynamic equilibrium modeling, multi-agent LLM systems) to interpret analytical data, predict extractant-metal selectivity, and drive AI-guided experimental studies via autonomous robotic laboratories for critical materials separation.
Role type
Senior IC computational scientist (materials science & AI)
Builds
AI-guided open-loop and closed-loop experimental studies for critical materials separation
Domain
Materials science, computational chemistry, AI/ML, robotics
Deliverable
production ML models
Required skills
Python, cheminformatics (RDKit), scientific machine learning (PyTorch Geometric), graph neural networks, thermodynamic equilibrium modeling, coordination chemistry, solution thermodynamics, aqueous electrolyte equilibria, Linux HPC, autonomous robotic lab interfacing
Preferred skills
PHREEQC/phreeqpy, non-ideal electrolyte models (Pitzer, Bromley, e-NRTL), wet-chemical lab handling, automated liquid handlers, analytical instrumentation (ICP-MS, ICP-OES, UV-Vis, ATR-FTIR), image segmentation (OpenCV, YOLOv8), hydrometallurgical feedstocks, grant writing
