Description

Cloud to Street is the leading flood mapping platform designed to protect the world’s most climate-vulnerable communities. By harnessing global satellites, advanced science, and community intelligence, we monitor worldwide floods in near real-time and remotely analyze local flood exposure at a click of a button. Our mission is to ensure that all vulnerable governments finally access the high quality information they need to prepare for and respond to increasing catastrophes. Founded by two women at Yale and seeded by Google, Cloud to Street is or has been used by governments across 15 countries. We are on track to enable new flood protection and insurance for 10 million people in the next 5 years.

As a Cloud to Street team member, you:
  • Lead development of rigorous science at start-up technology company focused on social impact and represent our organization at scientific and development meetings
  • Serve the underserved by reducing the scientific barriers for low and middle income countries to access the information governments, businesses, and communities need to sustainably develop and thrive
  • Are in solidarity with vulnerable communities by spending time with flood affected populations and organizations who serve them
  • Increase equity by making information accessible to historically marginalized communities and building a diverse and inclusive start-up

We are looking for a best-in-class data fusion scientist to lead innovation to downscale passive microwave sensors using radar and optical high resolution flood maps. You should apply if you are eager to use science to reduce the impact of catastrophic flooding and build an innovative and sustainable organization. In this role, you will lead the development of machine learning based algorithms trained on high resolution flood events to downscale passive microwave sensors. You will work with a team of scientists and engineers with expertise in remote sensing (optical, radar, and passive microwave), hydrology, climate, social vulnerability, UX, and machine learning to i) optimize and improve Cloud to Street’s current flood mapping system and ii) build the next generation of tools to ensure financial protection from floods in marginalized communities.

Skills and responsibilities

  • Develop new and incorporate existing flood detection methods at the forefront of science and technology
  • Improve Cloud to Street’s existing algorithms to extract data from passive microwave satellites and other sensors
  • Design and manage product development pipelines in response to needs from  governments, aid agencies, and insurers
  • Collaborate with a team of exceptional scientists and engineers that want you to grow and be successful
  • You tell us! Each member has skills not in their job description that are important for our growth. We would love to hear your unique talents and how we can help each other grow.   

Details

  • Location:
    Brooklyn
    ,
    NY
    Brooklyn, NY preferred; remote work possible for the right candidate
  • This job is remote friendly.
  • Deadline:
    2020-02-24

Qualifications

Minimum qualifications

  • Master’s or PhD in geography, earth science, atmospheric science, engineering, computer science, or a related field with a focus on remote sensing and/or geospatial analysis 
  • Scientifically sound approach to machine learning enabled data fusion, especially with computer vision techniques
  • Code proficiency in python
  • Self-starter with ability to work within a fast-paced and rapid-evolving startup
  • Eagerness to learn new skills and help with the task at hand
  • Prioritizes justice, diversity, science, and solidarity with vulnerable communities

Preferred qualifications

  • Coding proficiency using Google Earth Engine JavaScript and/or Python APIs, and/or open source geospatial Python packages
  • Experience using machine learning to develop products or in industry
  • Experience downscaling coarse resolution satellite imagery
  • Experience with data fusion or data assimilation with satellite imagery, especially using random forests or convolutional neural networks
  • Understanding of hydrology and physically-based flood models 
  • Contributing to a shared codebase on GitHub with multiple collaborators
  • Using virtual machines on Google Cloud or similar platform
  • Working in disaster relief or in low or middle-income countries