Brightband launches NNJA-AI v1 dataset Read more

Opportunity

  • Be one of the first hires at a remote-first startup founded by experienced entrepreneurs and developing a transformative approach to earth system modeling.
  • Build the world’s best weather forecast using a data-driven, end-to-end learned approach.
  • Work with high autonomy in a fast-paced environment, owning projects that span both research and production systems.
  • Join a multi-disciplinary team committed to open science and sharing results with the broader weather and climate communities.

Requirements

  • MS or PhD in computer science, mathematics, machine learning, physics, atmospheric science, or equivalent industry experience.
  • Strong understanding of machine learning and statistical methods.
  • Proficiency in deep learning frameworks like PyTorch, JAX, or TensorFlow.
  • Proficiency in running, analyzing, and troubleshooting ML experiments and workflows.
  • Track record of driving technically complex projects from start to finish.
  • Flexibility and adaptability to work on diverse projects and pivot when necessary.
  • A positive, solutions-focused approach to tackling technical challenges.

Great to Have

  • 3+ years of industry experience
  • Hands-on experience with ML architectures such as graph neural networks, transformers, and diffusion models.
  • A background in applying deep learning to spatiotemporal systems (weather, fluids, etc.).
  • Experience working with physical sensor data.
  • Experience with distributed, multi-node training of ML models.
  • Familiarity with the basic principles of numerical weather prediction and data assimilation.
  • Strong software engineering fundamentals for ML: writing maintainable, scalable code, and designing modular ML pipelines.
  • Experience improving ML systems used by real customers or end-users.

Responsibilities

  • Identify and prototype promising ML approaches from the broader research community.
  • Conduct experiments, analyze results, and scale up approaches that demonstrate experimental success.
  • Iteratively improve the models that power our production forecasts, ensuring high-quality outputs for customers.
  • Promote engineering and research best practices by conducting code reviews and ensuring high-quality code.
  • Collaborate with a small, focused team to advance the state of the art in weather forecasting using a data-driven, end-to-end learned approach.

Apply now