Science is at the heart of everything we do at Google DeepMind; it inspired us to build better algorithms. Now, our interdisciplinary team combines specialists with backgrounds in machine learning, computer science, physics, and more to build new methods that will push the boundaries of what is possible and help solve the biggest problems facing humanity. We have already made a number of high profile breakthroughs applying machine learning in the Fusion space, and we have all the ingredients in place to make further significant progress over the coming years.
About UsGoogle DeepMind (GDM) is pursuing a ground-breaking research program to enable safe, high-yield fusion energy as quickly as possible, with a group of research scientists and engineers on a mission-driven team. Together, you will help apply ML and other computational techniques to a wide range of challenging problems in Fusion. You’ll join an interdisciplinary team developing and running experiments in simulation and in the real world. Some public examples of our recent work are reinforcement algorithms for tokamak control, development of JAX-based simulators, and our recent announcement of our research partnership with Commonwealth Fusion Systems.
The RoleSuccessful applicants should be passionate about the use of AI in Fusion.
As a Research Scientist within Fusion, you will use your expertise to push forward Google Deepmind’s investment in Fusion energy. You will be working with in-house scientists and engineers to push forward DeepMind’s work in hybrid data and physics-driven predictions and applications for pulse design and control.
Key responsibilities:- Advance predictive capabilities to beyond the state-of-the-art by combining data-driven and physics-based approaches at scale.
- Collaborate with other physicists, engineers and ML researchers across the team on designing and implementing systems for magnetic confinement fusion pulse optimization and controller design.
- Employ cutting-edge technology and techniques to contribute to solving some of the hardest problems.
- Incorporate your passion for science and any previous knowledge or academic experience to join a team of hardworking individuals who openly collaborate with one another and cultivate a culture of continuous development and advancement.
In order to set you up for success as a Research Scientist at Google DeepMind, we look for the following skills and experience:
- PhD or MSc in physics, computer science or equivalent industry experience.
- Established experience in a magnetic confinement fusion research environment.
- Familiarity with magnetic confinement fusion datasets, and a passion for utilizing data at scale to push research boundaries.
- Proven ability to navigate ambiguous challenges and translate high-level goals into progress.
- Passion for accelerating science using innovative technologies.
In addition, the following would be an advantage:
- Proven experience in Python development.
- Significant experience working with data and building pipelines.
- Experience in magnetic confinement fusion integrated modelling.
- Experience applying machine learning techniques to problems in fusion.
- Direct experience in tokamak experiments and operation.
- Strong understanding of trends and advances within plasma physics and fusion energy, especially within magnetic confinement.
We encourage you to apply if you're excited about this role, even if your experience doesn't perfectly match every qualification.
At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law. If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.
