Fervo is building a dedicated AI team to unlock transformational value across drilling, reservoir modeling, operations, and commercial strategy to accelerate geothermal development.
Requirements
- Strong proficiency in Python and machine learning frameworks (e.g., PyTorch, TensorFlow, Scikit-learn)
- Demonstrated research experience in one or more of: large language models, time-series analysis, physics-informed ML, optimization, or reinforcement learning
- Ability to apply theoretical knowledge to practical, messy, real-world datasets
- Experience with energy systems, industrial operations, or geoscience applications
- Prior experience with RAG architectures, data engineering, or scalable model deployment
- PhD candidate in Computer Science, Applied Mathematics, or a related quantitative field with a focus on AI/ML
Responsibilities
- Develop, train, and evaluate advanced AI models (LLMs, ML, time-series, hybrid physics-informed)
- Collaborate with end-user teams to scope and deliver applied AI solutions
- Contribute to Fervo’s centralized AI infrastructure and data architecture
- Document methodologies and provide clear technical communication to technical and non-technical stakeholders
- Present findings and recommendations to cross-functional teams, including senior leadership
- Designing hybrid AI-physics models for subsurface forecasting
- Developing machine learning algorithms for real-time drilling optimization
Other
- PhD candidate in Computer Science, Applied Mathematics, or a related quantitative field with a focus on AI/ML
- Excellent problem-solving, communication and collaboration skills
- Self-starter with the ability to scope and drive projects independently
- regular in-office presence at our Houston Office will be required.
