Staff ML Data Scientist

6 days ago

Apply Now

Receive Emails with Similar Jobs

KoBold Metals

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2019

🤖 Artificial Intelligence

🔬 Science

⚡ Energy

Description

• Hyperspectral airborne and satellite images, radar, lidar, and radiometrics offer a tremendous amount of information for modeling the Earth’s crust to discover mineral resources to enable the energy transition. • Reporting to the VP of Technology, responsibilities of this position include: • Architect, implement, and maintain foundational data science models for distributed processing of large-scale geospatial data with direct application to Kobold’s mineral exploration projects and deep collaboration with geoscientists. • In collaboration with our engineering team, build tooling to increase the velocity and rigor of our machine learning capabilities to derive insights from remote sensing data. • Improve upon current processing pipelines for lidar, high resolution imagery, and hyperspectral data. • Push the state of the art in analysis capabilities by implementing statistically rigorous spatially aware clustering, anomaly detection, and other analysis methods. • Collaborate with data scientists, geoscientists and engineers to invent and deploy algorithms that combine large and complex data sets for mineral exploration and discoveries.

Requirements

• At least 5 years of experience as a software engineer, data scientist or ML engineer, though most great candidates will have closer to 10. Recent bachelor’s/master’s/PhD candidates are unlikely to be competitive. • 2+ years managing technical teams in complex, multidisciplinary projects • Track record of building production quality data processing solutions or tooling that have delivered business value • Proficiency with foundational concepts of ML, including statistical, traditional and deep-learning approaches • Proficiency in Python, ideally including array-based packages such as xarray and numpy • Proficiency in scaling complex data operations across distributed computing resources, using tools such as Spark or Dask • Capacity to dive deep on novel challenging problems in applying ML to mineral exploration, including understanding a complex domain of geology and mineral exploration practices as well as working with limited, disparate and noisy data sources • Collaborative attitude to work with stakeholders with different backgrounds (data scientists, geoscientists, software engineers, operations) • Experience with multispectral remote-sensing data from a variety of sources