Research Scientist, AI for (Sub)seasonal Weather Forecasting

Snapshot

We've built a unique culture and work environment where ambitious, long-term research can flourish and be translated into societal benefits. We've made high-profile breakthroughs for medium-range weather forecasting (e.g., GraphCast, GenCast) and are now extending this work into the 2-week to 3-month (subseasonal) range. We are seeking a Research Scientist to help drive this exciting research.

About Us

Our mission is to create the world’s most trustworthy and useful weather forecasts for the benefit of humanity. Research is central to our mission, but we also ensure that our research can be turned into tangible impact that benefits humanity. Our interdisciplinary team combines the best techniques from machine learning, statistics, and meteorology to build the science for the best weather forecasting systems. Our approach encourages collaboration across all groups within the research team, cultivating ambitious creativity and innovative research. 

The Role

Research Scientists are encouraged to lead or support a research agenda that produces practical technological advances in weather forecasting.

The expectation is that research scientists will conduct novel research according to ambitious long-term agendas, while maintaining a strong focus on methods and tools offering practical benefits in the short term as a form of pragmatic grounding. Central to this process is the idea that rapid iteration and refinement of solutions for real-world use cases provides a strong basis for better understanding the frontiers of research in this fast-paced field.

Key responsibilities:

• Contribute (and lead) the ideation and development of new data-driven approaches to (sub)seasonal weather forecasting advised by the current state of research.

• Partner with research engineers to develop ambitious prototypes and design and implement evaluation protocols around these prototypes.

• Identify roadblocks and research challenges by empirically or theoretically studying the failures and limitations of existing methods.

• Develop novel technical or methodological solutions to overcome these obstacles and limitations.

• Help identify, within Google’s broad portfolio of research projects, methods which could be adapted or tried against our evaluations, as well as teams and individuals with which the team could partner to overcome challenges whilst providing grounding and evaluation for that collaborator's research agenda.

• Digest and understand complex research papers, theory and practice.

• Own, report and present (verbally and in writing) research developments and experimental results to both the immediate and broader research teams, as well as externally. 

• Promote scientific excellence through mentoring and reviewing.

The Team

Our team is especially focused on:

• Machine learning (ML) for weather modelling and forecasting.

• Graph neural networks, diffusion models.

• Scalable Bayesian inference.

• Climate and sustainability-related research.

• A variety of complex problems to work on, with the opportunity to learn constantly through experimentation. 

• Access to a team of leading researchers, engineers, and problem solvers to learn from, with the opportunity to contribute your own thinking and specialist knowledge to our mission.

• Constant learning, training, and development opportunities—from technical courses to improving presentation skills—to help you design a career that works best for you.

• Access to leading technology, ever-evolving tech stacks, and Google-scale systems to allow your work to flourish.

• An opportunity to make contributions to addressing societal challenges.

About you

In order to set you up for success as a Research Scientist at Google DeepMind, we look for the following skills and experience:

• PhD degree in a relevant field.

• Proven knowledge of ML and/or statistics, e.g., deep learning.

• Proven experience working on weather forecasting in either an industry or a research lab setting.

• Strong knowledge and experience of Python.

• Working knowledge of Jax, TensorFlow, or similar frameworks.

• Experience with research and publishing, e.g., authored papers.

In addition, the following would be an advantage: 

• Experience with simulators, partial differential equations, and/or numerical methods.

• Experience with modelling of other environmental systems (e.g., oceans, sea ice).

• Experience in ML for the physical sciences and/or sustainability.

• Experience with large-scale and/or distributed computing.

 

Closing date: Wednesday, 20th August at 5:00pm BST

 

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.