Research Software Engineer - Scientific Computing & GPU Infrastructure

Marvel Fusion Inc.

München

On-site

EUR 90,000 - 130,000

Full time

8 days ago

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Public Transport Subsidy

Employee Incentive Program

Wellpass or Complimentary Private High

Professional Learning & Development预算

Relocation Support

Company Pension Plan

30 Days of Vacation plus additional ½‑

30 Days of Vacation plus additional ½

Modern Office in the center of Munich

Healthy office snacks

Regular Team Events

Job summary

Marvel Fusion Inc. is seeking a Research Software Engineer in Munich to advance computational challenges in fusion research. You will develop scientific Python software, work with physicists, and turn ideas into reliable software, including GPU computing on NVIDIA servers and in the cloud.

You will contribute to performance analysis and automated workflows. You will collaborate across teams, implement reproducible environments, and help extend testing, CI, packaging, and documentation to support

Qualifications

Strong Python software engineering skills and a track record of delivering maintainable software
Experience with scientific or numerical computing and verifying numerical accuracy
Hands-on experience deploying Python or GPU workloads on remote Linux servers or cloud infrastructure
Experience profiling computational workloads and using GPU computing frameworks
Excellent written and verbal English communication skills

Responsibilities

Develop and maintain scientific Python software, turning research requirements into reusable, tested features and clear interfaces
Collaborate with scientists to define acceptance criteria and verify numerical results against reference cases and accuracy requirements
Use profiling to identify bottlenecks; compare algorithms, code translations and CPU/GPU implementations
Prepare and deploy scientific workloads on NVIDIA GPU servers or AWS using reproducible environments and automated workflows
Work with IT to support multiple users through access controls, job scheduling, resource allocation, monitoring and storage
Connect computational services to internal applications through stable APIs for job submission, status tracking and result retrieval
Improve testing, CI, packaging and documentation, and independently carry tasks through to delivery

Skills

Python

Software engineering

Numerical computing

English communication

Education

Degree in Computer Science, Physics, Applied Mathematics or Engineering

Tools

CuPy

PyTorch

JAX

CUDA

Job description

Research Software Engineer - Scientific Computing & GPU Infrastructure

Who we are

Founded in 2019, Marvel Fusion is Europe’s leading fusion energy company, uniting 120 scientists, engineers, and entrepreneurs across our locations in Munich and Colorado .

Backed by over €385 million in public and private funding, we’re driven by a shared mission: to deliver clean, abundant energy to the world.

Why Marvel Fusion

By joining us, you will be:

Solving one of the most complex technological challenges known to humanity, harnessing Fusion on Earth
Part of a highly purpose-driven team working on providing the world with clean, safe and abundant energy
Working alongside world-leading scientists and entrepreneurs in the field of Fusion
Part of a start-up where growth on a company and individual level is the default

The impact you will make

As part of our multidisciplinary research and engineering team, you will shape how we tackle computational challenges in fusion research. You will combine your software expertise with the team’s knowledge of physics and engineering to develop new approaches, make technical decisions and turn ideas into reliable scientific software. From advancing numerical performance to enabling shared GPU computing on NVIDIA servers or AWS, you will own meaningful technical challenges and contribute directly to our scientific progress.

Your responsibilities

Develop and maintain scientific Python software, turning research requirements into reusable, tested features and clear interfaces.
Work with scientists to define acceptance criteria and verify numerical results against reference cases and agreed accuracy requirements.
Use profiling to identify bottlenecks; compare algorithms, code translations and CPU/GPU implementations through reproducible benchmarks.
Prepare and deploy scientific workloads on NVIDIA GPU servers or AWS using reproducible environments and automated execution workflows.
Work with IT to support multiple users through appropriate access controls, job scheduling, resource allocation, monitoring and result storage.
Connect computational services to internal applications through stable APIs for job submission, status tracking and result retrieval.
Improve testing, continuous integration, packaging and documentation, and independently carry agreed development tasks through to delivery.

What you bring

A degree in Computer Science, Physics, Applied Mathematics, Engineering or a related field, or equivalent practical experience.
Strong Python software engineering skills and a track record of independently delivering maintainable software within an existing codebase.
Experience with scientific or numerical computing, including testing numerical accuracy and collaborating with domain experts.
Practical experience profiling computational workloads and using GPU computing frameworks such as CuPy, PyTorch, JAX or CUDA.
Hands-on experience deploying scientific Python or GPU workloads on remote Linux servers or cloud infrastructure, including reproducible environments, job execution and data handling.
A structured approach to debugging, version control, automated testing and documentation, with the ability to make pragmatic engineering decisions.
A self-driven, collaborative working style and excellent written and verbal communication skills in English.

Nice to have

Direct experience with AWS GPU services or shared NVIDIA GPU infrastructure, including containers, workload scheduling or monitoring.
Expertise in CUDA, multi-GPU computing, high-performance computing or performance-portable numerical software.
Experience integrating scientific applications with compute services, or a background in optics, photonics or experimental data analysis.
Experience evaluating AI-based acceleration of scientific workloads against accuracy and runtime benchmarks.

What we offer

Our mission is motivation enough for many. But we also support our team with benefits that foster wellbeing and growth: