SciML Scientist for Fusion Plasma & Real-time Control

Fusionality; Lausanne; On-site; CHF 100,000 - 170,000; Full time

Benefits offered by this job

Immigration assistance

Equity compensation

Job summary

Fusionality in Lausanne, Switzerland, is building a measurement, simulation, and control stack for future fusion reactors. We seek a PhD-level or senior Computational Scientist specializing in Scientific Machine Learning (SciML) to develop fast, differentiable solvers and run them on real plasma data and control systems.

You will implement solvers in JAX (with Julia or PyTorch as a fallback), advance numerical methods for ODEs/PDEs, and ensure production-grade performance.

Qualifications

• PhD or equivalent research experience in SciML or related field.
• Strong background in numerical methods for ODEs/PDEs and implicit solvers.
• Experience with differentiable frameworks (JAX, Julia, PyTorch) and large codebases.

Responsibilities

• Design, implement and validate differentiable solvers in JAX for plasma physics problems.
• Optimize performance for production use on GPU/TPU with advanced numerical techniques.
• Apply automatic differentiation for model calibration and controller design with experimental data.
• Ensure code quality, testing, verification against reference solutions, packaging and documentation.

Skills

SciML

Differentiable solvers

JAX

ODEs & PDEs

Python

Education

PhD or equivalent

Tools

JAX

Julia

PyTorch

Job description

Fusionality in Lausanne, Switzerland, is building a measurement, simulation, and control stack for future fusion reactors. We seek a PhD-level or senior Computational Scientist specializing in Scientific Machine Learning (SciML) to develop fast, differentiable solvers and run them on real plasma data and control systems.

You will implement solvers in JAX (with Julia or PyTorch as a fallback), advance numerical methods for ODEs/PDEs, and ensure production-grade performance.