Lead Data Scientist - Subsurface ML & Large-Scale Learning

TGS; Houston (TX); On-site; USD 140,000 - 210,000; Full time

Job summary

TGS seeks a Lead Data Scientist to advance scientific machine learning for complex subsurface problems, combining hands‑on model development with technical leadership across major initiatives. You will help build reusable learning systems for subsurface data and guide cross‑team collaboration with senior data scientists and engineering partners.

The role emphasizes scientific rigor, reproducibility, and mentorship, contributing to the design and deployment of large‑scale learning systems within

Qualifications

• Requires MSc/PhD in a technical field.
• 5–10 years of applied data science or research‑oriented ML.
• Strong background in deep learning and scientific ML for large datasets.
• Experience leading technical initiatives or complex modeling projects.
• Energy, geoscience, or large‑scale industrial domains preferred.

Responsibilities

• Lead design, implementation, and evaluation of scientific ML models for subsurface and energy data.
• Guide development of large-scale representation learning systems.
• Provide technical reviews to ensure robustness, generalization, and reproducibility.
• Own major workstreams from research to deployment.
• Collaborate with senior data scientists, domain experts, and engineers.
• Mentor data scientists and share knowledge across the org.
• Engage in external research activities and publications.

Skills

Scientific ML

Leadership

Experimentation

Collaboration

Mentorship

Education

MSc/PhD in ML/Data Science

Tools

Deep Learning Frameworks

Representation Learning

Job description

TGS seeks a Lead Data Scientist to advance scientific machine learning for complex subsurface problems, combining hands‑on model development with technical leadership across major initiatives. You will help build reusable learning systems for subsurface data and guide cross‑team collaboration with senior data scientists and engineering partners.

The role emphasizes scientific rigor, reproducibility, and mentorship, contributing to the design and deployment of large‑scale learning systems within