Description:

The Staff Machine Learning Engineer will lead the development of a generative model that produces 3D geological models based on geophysical surveys, borehole measurements, and other physical observations.
This role aims to enhance decision-making in the earth subsurface for various clean energy applications.
Responsibilities include designing, training, testing, and iterating on diffusion models for 3D geological models.
The engineer will also design and implement methods for conditioning generation on geophysical data and other observations.
Informing the generation of synthetic data to improve model performance is a key responsibility.
The role requires adapting diffusion modeling approaches to specific real-world projects in collaboration with project teams.

Requirements:

Extensive experience with PyTorch is required, including the ability to write custom modules, optimize training, and debug issues in large-scale models.
Candidates must have expertise in developing large deep learning models from scratch, demonstrating the ability to design, implement, and train complex architectures.
Data curation skills are necessary, with hands-on experience in creating, cleaning, and maintaining high-quality datasets for machine learning applications.
Strong software engineering and design experience is essential, including proficiency in software development best practices such as version control, testing, and code optimization.
Familiarity with designing scalable and maintainable systems is also required.
Bonus points for candidates with experience in generative models, particularly diffusion models, and knowledge of posterior sampling methods.
Knowledge of transformer architectures and experience in building and training transformers for 3D data applications is a plus.
Expertise in scaling models across large GPU clusters and optimizing distributed training pipelines is advantageous.
Experience in cloud infrastructure, including setting up, managing, and optimizing cloud environments for machine learning workloads, is beneficial.

The position offers the opportunity to work remotely from anywhere in the US.
Employees will be part of a pioneering team that is revolutionizing decision-making in clean energy applications.
The role provides a chance to work on cutting-edge technology in the field of machine learning and geoscience.
There are opportunities for professional growth and development within the organization.
The company promotes a collaborative work environment that encourages innovation and creativity.