Responsibilities:

• Architect, implement, and maintain foundational scientific computing libraries that will be used in KoBold’s mineral exploration analyses.
• Build tooling to increase the velocity of our machine learning progress, including enabling rapid prototyping in Jupyter notebooks; build experimentation, evaluation, and simulation frameworks; turning successful R&D into robust, scalable ML pipelines; and organizing models and their outputs for repeatability and discoverability.
• In collaboration with data scientists, build models to make statistically valid predictions about the locations of economic concentrations of ore metals within the Earth’s crust.
• Apply–and coach team members to use–engineering best practices such as writing robust, testable and composable code
• Collaborate with data scientists, geoscientists and engineers to invent the modern scientific computing stack for mineral exploration
• Occasional travel to exploration sites around the world to observe the impact of scientific computing on KoBold’s exploration products and design new technologies to further discovery. Travel is approximately twice per year depending on project needs.

Qualifications:

• At least 5 years of experience as a software engineer, data scientist or ML engineer, though most great candidates will have closer to 10.
• 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
• Deep experience with measured scientific data
• Experience in visualizing scientific data for domain experts
• Experience in MLops and in the making of robust ML systems
• Drive to increase the velocity and effectiveness of our data scientists in both experimental and production workflows
• 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)

Work practices and motivation:

• Ability to take ownership and responsibility of large projects.
• Intellectual curiosity and eagerness to learn about all aspects of mineral exploration, particularly in the geology domain. Open to working directly with geologists in the field. Enjoys constantly learning such that you are driving insights and innovations.
• Ability to explain technical problems to and collaborate on solutions with domain experts who aren’t software developers. A strong communicator who enjoys working with colleagues across the company.
• Excitement about joining a fast-growing early-stage company, comfort with a dynamic work environment, and eagerness to take on a range of responsibilities.
• Keen not just to build cool technology, but to figure out what technical product to build to best achieve the business objectives of the company.
• Ability to independently prioritize multiple tasks effectively.

XML job scraping automation by YubHub

Key responsibilities include pioneering novel computer vision models to create a unified understanding of agriculture from diverse satellite data sources, solving core AI problems by developing generalizable models that are robust across varied agricultural systems, leading research toward the grand challenge of field-level crop yield forecasting, designing and executing large-scale experiments, writing high-quality, reusable code, and contributing to a production-ready system.

You will also mentor junior researchers, collaborate with cross-functional teams across Google, and publish your work at top-tier conferences.

We are looking for a passionate and talented researcher with a strong foundation and a proven ability to conduct impactful research in AI. You should have a PhD or equivalent practical research experience in Computer Science, AI, or a related field with a focus on computer vision and/or machine learning, a strong publication record in top-tier AI conferences, hands-on experience building and training deep learning models in frameworks such as JAX, TensorFlow, or PyTorch, and demonstrated expertise in one or more of the following: generative models, segmentation algorithms, multi-modal fusion, spatio-temporal analysis.

XML job scraping automation by YubHub