Staff Machine Learning Engineer

ZipRecruiter; Redwood City (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

An innovative company is seeking a talented deep learning engineer to lead the development of groundbreaking generative models for 3D geological applications. This role involves designing and iterating on diffusion models, conditioning on geophysical data, and enhancing model performance through synthetic data generation. Join a forward-thinking team that is revolutionizing decision-making in clean energy exploration, where your expertise will shape the future of subsurface resource management. If you are passionate about deep learning and eager to tackle complex challenges, this opportunity is perfect for you.

Qualifications

• Extensive experience with PyTorch and large-scale models.
• Strong software engineering skills and design experience.

Responsibilities

• Design, train, and test diffusion models for 3D geological models.
• Collaborate with project teams to adapt modeling approaches.

Skills

PyTorch

Deep Learning

Data Curation

Software Engineering

Version Control

Job description

Job Description

Role description

In the same way image generators have shown the remarkable ability to produce a diverse set of realistic pictures conditioned on a text prompt (and other inputs), we are developing a generative model that produces 3D geological models conditioned on geophysical surveys, borehole measurements, and other forms of physical observation. The outputs of the generative model capture what we know and don’t know about the state of the subsurface, allowing explorers to make maximally informed decisions about how and where to explore for critical resources.

We are looking for a talented deep learning engineer or scientist to lead the development of this model that will revolutionize decision-making in the earth subsurface for a wide range of clean energy applications.

Role Responsibilities

1. Design, train, test, and iterate on diffusion models for 3D geological models
2. Design, train, test, and iterate on an approach to conditioning on geophysical data and other observations
3. Inform the generation of synthetic data to improve model performance
4. Adapt diffusion modeling approach to specific real-world projects in collaboration with project teams

Qualifications

Required Qualifications:

• Extensive PyTorch experience, including writing custom modules, optimizing training, and debugging issues in large-scale models
• Expertise in developing large deep learning models from scratch, with a proven ability to design, implement, and train complex architectures
• Data curation skills, including creating, cleaning, and maintaining high-quality datasets for machine learning applications
• Strong software engineering and design experience, including version control, testing, and code optimization; familiarity with designing scalable and maintainable systems

Bonus points if you:

• Have experience with generative models, especially diffusion architectures and posterior sampling methods
• Know transformer architectures and have experience building and training transformers for 3D data applications
• Have experience scaling models across large GPU clusters and optimizing distributed training pipelines
• Possess cloud infrastructure expertise, including setting up, managing, and optimizing cloud environments for machine learning workloads, resource provisioning, and cost management