Machine Learning Scientist

Zanskar is seeking a full-time Machine Learning Scientist in Salt Lake City, UT, to enhance geothermal energy development through AI tools and algorithms. The role involves model training, geospatial data processing, and application development. Candidates should have 5+ years of experience in machine learning, preferably with geospatial applications, and strong skills in Python and SQL. This position is hybrid, indicating some in-office presence is required.
Role Overview
Title: Machine Learning Scientist
Hours: Full-Time, Salaried
Location: Salt Lake City, UT, Hybrid
Benefits Eligible: Yes
Manager: Sr Machine Learning Engineer, Rachel Morrison

Mission - Why we need you

Geothermal energy is the most abundant renewable energy source in the world. There is 2,300 times more energy in geothermal heat in the ground than in oil, gas, coal, and methane combined. However, historically it’s been hard to find and expensive to develop. At Zanskar, we’re using better technology to find and develop new geothermal resources in order to make geothermal a cheap and vital contributor to a carbon-free electrical grid.

The Machine Learning Scientist will play a critical role in accelerating our goals of rapid development of geothermal energy in the US. Although geothermal is abundant, there is extreme geographic variability in how accessible it is at shallow depths that are commercially viable. Finding a resource is a time and labor-intensive process of identifying targets, drilling exploration wells, and collecting other field data. This process requires significant upfront costs with highly uncertain outcomes. The Scientist’s role will be to help Zanskar achieve its mission to augment, automate, and optimize these processes with custom AI tools and algorithms. Successful work will de-risk the process, discover resources that would remain hidden, and drive down development costs.

Outcomes - Problems you’ll solve

The geological factors that make our work difficult and interesting are temperature and depth heterogeneity resulting largely from differences in the underlying source of heat (e.g., magmatism, radioactivity) as well as the processes of heat transfer (e.g., conductive, convective) and where those favorably intersect other commercial factors like access to the grid. In the first six months, you will refine and develop apps & algorithms using various datasets to unlock our ability to predict geothermal potential including:

Model Training and Evaluation: Develop, train, and evaluate models for tasks such as image recognition, object detection, spatial analytics, etc.
Geospatial Data Processing: Work with large-scale geospatial datasets, applying advanced techniques to extract meaningful insights.
Application Development and Deployment: Design and implement web applications to facilitate data ingestion, data exploration and QC, automation tasks, and deployment of machine learning models.
Infrastructure: Leverage our data science infrastructure (cloud compute, Github, Docker, CI/CD pipelines, SQL database, Terraform, etc.)

What we’re looking for

Experienced intersection of ML & Geospatial programming: Minimum 5+ years experience in machine learning and/or data science in a business environment. Master's or Ph.D. in Computer Science, Machine Learning, Geostatistics, Geophysics, or similar preferred. Higher level candidates will be considered for Senior Machine Learning Scientist.

Skills include:
- Proven experience in developing and deploying machine learning models in a business setting, preferably with a focus on deep learning, geospatial applications (e.g., satellite data analysis), and/or computer vision.
- Proven experience developing and deploying dashboards and web applications (e.g., Superset, Panel) in a business setting.
- Strong programming skills in Python and SQL and experience with machine learning libraries/frameworks (e.g., scikit-learn, PyTorch, and/or PyTorchLightning)
- A commitment to coding best practices (version control, peer review, documentation, CI/CD deployment, etc.)
- Familiarity with geospatial data formats, GIS tools, and geospatial libraries (GDAL, GeoPandas, etc.)
- Strong mathematical and statistics background. Bayesian statistics and decision analysis theory are large bonuses.

Strong collaborator: The AI team interacts closely with geoscientists, land leasing, project finance, field technicians, and others to make sure the tools they build create real impact on development decisions. The Scientist must be able to translate business requirements into technical solutions and communicate/collaborate with a variety of stakeholders.

Intrinsically motivated: Zanskar is a team of mission-oriented professionals who live by the value “Blaze a Trail, Leave a Legacy.” We work on problems no one else has solved before, so we need curious self-starters with a strong penchant for solving complex ML problems.

Job posting details for Machine Learning Scientist at Zanskar in Salt Lake City, Utah. . ClimateTechList gathers 19,000+ job openings from over 911 climate tech companies and updates them daily.