Principal Plasma Data Scientist

Helion Energy•Everett, WA

7h•Onsite

About The Position

Helion is hiring a Plasma Data Scientist specializing in physics‑grounded machine learning to accelerate experimental FRC plasma modeling. This role will focus on developing and validating advanced ML frameworks—such as differentiable‑physics models, PINNs, surrogate modeling, or hybrid physics+ML systems—while integrating these tools with simulation and diagnostics pipelines. You will support cross‑disciplinary fusion research and contribute to high‑impact modeling that informs experimental design and interpretation. This onsite position reports to the Experimental Science Manager at our Everett, WA office and plays a key role in advancing fusion electricity development.

Requirements

PhD in Physics, Engineering, Applied Math, Computational Science, Machine Learning, or related field with emphasis on physics‑grounded modeling
10+ years of industry or research‑lab experience applying machine learning in experimental, simulation‑driven, or scientific R&D environments
Expertise with physics‑informed or physics‑constrained ML methods, such as differentiable physics, PINNs, scientific ML, surrogate modeling, or reduced‑order models for complex physical systems
Experience integrating ML models with scientific‑computing workflows, simulation tools, or experimental diagnostics
Proficiency scripting for data parsing, model analysis, and visualization (MATLAB, Python, or similar; Fortran or HPC exposure valuable)
Familiarity with magnetic diffusion, circuit coupling, or plasma‑dynamics modeling in pulsed‑power or electromagnetics systems

Responsibilities

Develop and validate machine‑learning frameworks for FRC plasma‑dynamics, leveraging physics‑grounded ML approaches (e.g., differentiable physics, PINNs, surrogate modeling, or hybrid physics+ML systems)
Integrate ML models with existing simulation tools and experimental‑diagnostic pipelines to enable hybrid physics + data‑driven validation workflows
Reproduce experimental plasma conditions within ML modeling workflows to support interpretation of magnetic diffusion, circuit response, and diagnostic measurements
Generate analysis scripts for post‑processing, parsing model outputs, and visualizing correlations between ML‑based predictions and experimental results
Collaborate with plasma‑physics, pulsed‑power, and transient‑magnetics experts to expand the fidelity and fusion‑relevance of ML‑enabled modeling frameworks
Communicate results with rigor and clarity through reports, presentations, and technical visualizations for research stakeholders