Remote Staff Data Scientist

Logo of KoBold Metals

KoBold Metals

πŸ’΅ $190k-$235k
πŸ“Remote - Worldwide

Job highlights

Summary

Join KoBold, a leading mineral exploration company, as a Staff Data Scientist. You will build predictive models using scientific computing, statistical, and physics-based methods to locate ore deposits. This role involves developing a worldwide dataset, creating 2D and 3D geologic predictions, and collaborating with geoscientists and stakeholders. You will contribute to KoBold's proprietary software exploration tools and help guide exploration decisions. As an early team member, you'll build these tools from the ground up, accelerating the discovery of critical battery metals. This is a full-time, exempt position with a remote-first work environment.

Requirements

  • Possess extensive experience with Python’s data science packages and general software engineering practices
  • Be proficient in collaborative software development (git), and familiar with software engineering best practices like unit test / integration test suites, and CICD pipelines
  • Have experience with cloud computing resources
  • Have experience building predictive models, applying them to different problems, and evaluating and interpreting the results
  • Have experience working with data from a variety of physical systems
  • Have experience with geospatial analyses and visualizations
  • Possess broad skills in and knowledge of applied statistics and Bayesian inference
  • Have a substantial understanding of machine learning algorithms
  • Hold an advanced degree in the physical sciences, engineering, computer science, or mathematics
  • Have a minimum of 6 years post-degree work experience as a data scientist or data engineer
  • Have experience leading technical teams to apply novel scientific approaches to core business problems
  • Be able to design, scope and implement technical solutions to novel exploration problems
  • Demonstrate the ability to quickly absorb and synthesize complex information, with a track record of high intellectual rigor in a professional setting
  • Possess exceptional curiosity and eagerness to learn, with a proactive approach to exploring new concepts and technologies
  • Show excitement about joining a fast-growing early-stage company, comfort with a dynamic work environment, and eagerness to take on a range of responsibilities
  • Be able to independently prioritize multiple tasks effectively

Responsibilities

  • Help develop KoBold’s proprietary software exploration tools
  • Find and curate geophysical, geochemical, geologic, and geographic data and integrate it into KoBold’s proprietary data system
  • Build models to make statistically valid predictions about the locations of compositional anomalies within the Earth’s crust
  • Create effective visualizations for evaluating model performance and enabling rapid interaction with the underlying data and key features
  • Develop and apply data processing, statistical, and physics-based techniques to geoscientific data β€” from computer vision to geophysical inversions β€” and use the results to guide our targeting efforts and inform our acquisition and exploration decisions
  • Present to and collaborate with our external partners and stakeholders

Preferred Qualifications

  • Have experience creating machine learning models on geospatial data
  • Have experience with geostatistics
  • Have experience with image processing or computer vision
  • Have experience with distributed computing applications for machine learning and other computations

Benefits

  • Remote-first workplace
  • US base salary range for this full-time exempt position is $190,000-$235,000

Share this job:

Disclaimer: Please check that the job is real before you apply. Applying might take you to another website that we don't own. Please be aware that any actions taken during the application process are solely your responsibility, and we bear no responsibility for any outcomes.

Similar Remote Jobs

Please let KoBold Metals know you found this job on JobsCollider. Thanks! πŸ™