Ames National Laboratory Scientist I

Iowa State University•Ames, IA

2d•Onsite

About The Position

The successful candidate will serve as the computational lead within an integrated discovery platform for critical materials separation. The role involves architecting digital frameworks spanning graph neural networks, molecular representations, thermodynamic equilibrium modeling, and multi-agent large language model (LLM) systems. These frameworks will interpret complex analytical data, predict extractant-metal selectivity, and support AI-guided open-loop and closed-loop experimental studies through direct interaction with autonomous robotic laboratories. The position requires a strong foundation in coordination chemistry, solution thermodynamics, and aqueous electrolyte equilibria, as well as advanced programming skills in Python, RDKit, and scientific machine-learning frameworks such as PyTorch Geometric. The candidate will develop LLM-based agentic workflows, work in Linux-based high-performance computing environments, interface with autonomous robotic labs, and collaborate with multi-institutional teams to translate physical sciences into computational workflows. This is a one-year term appointment at Ames National Laboratory, located on the Iowa State University campus in Ames, Iowa. The incumbent must obtain and maintain government access authorization for the duration of the appointment. Employment is contingent on applicable Department of Energy and Iowa State University requirements, which may include background checks and eligibility determinations. Applicants must disclose participation in foreign-government-sponsored or affiliated activities as defined by DOE Order 486.1A.

Requirements

PhD or equivalent combination of education and experience.
Strong fundamental grasp of coordination chemistry, solution thermodynamics, and aqueous electrolyte equilibria.
Advanced programming proficiency in Python and cheminformatics libraries, specifically RDKit.
Experience with scientific machine-learning frameworks such as PyTorch Geometric.
Hands-on experience developing LLM-based agentic workflows.
Experience navigating Linux-based high-performance computing cluster environments.
Experience interfacing with autonomous robotic laboratories for open-loop and closed-loop studies.
Ability to work collaboratively in multi-institutional teams.
Ability to obtain and maintain government access authorization for the duration of the appointment.

Nice To Haves

Experience with aqueous equilibrium engines, specifically PHREEQC or phreeqpy, and familiarity with non-ideal electrolyte models such as Pitzer equations, Bromley, or e-NRTL.
Prior exposure to wet-chemical laboratory environments handling mineral acids, metal salt solutions, and organic solvent diluents.
Experience interfacing with autonomous robotic labs or automated liquid handlers for AI-guided open-loop and closed-loop experimental studies.
Familiarity with data from analytical instrumentation such as ICP-MS, ICP-OES, UV-Vis spectrophotometry, and ATR-FTIR.
Basic familiarity with OpenCV, YOLOv8, or simple image-segmentation tools.
Exposure to real-world hydrometallurgical feedstocks such as acid rock drainage, zinc roaster residues, and bauxite red mud.
Experience drafting research proposals or participating in grant writing.

Responsibilities

Serve as the computational lead within an integrated discovery platform.
Architect digital frameworks incorporating graph neural networks, molecular representations, thermodynamic equilibrium modeling, and multi-agent LLM systems.
Interpret complex analytical data and predict extractant-metal selectivity.
Drive AI-guided open-loop and closed-loop experimental studies through direct interaction with autonomous robotic laboratories.
Develop LLM-based agentic workflows and computational workflows that translate physical sciences.
Collaborate with multi-institutional teams.