Accelerated Science Intern, Representation Learning for Molecules and Materials

About the role#

We are looking for a researcher or engineer to study how machine learning models represent molecules and materials. You will work with our team to determine if different models discover the same underlying physical structure. This role involves mathematical reasoning and computational experiments to understand how training data, learning objectives, and model architectures shape these representations. You will explore when models arrive at shared representations, what information they capture, and how they relate to the physics of the systems under study.

What you'll do#

• Implement and evaluate machine learning models for molecules and materials using reproducible workflows.
• Design controlled experiments to study how learned representations vary across training runs, architectures, and learning objectives.
• Investigate the geometry and information content of learned representations and their connection to physical quantities.
• Develop methods to distinguish meaningful shared structure from similarities caused by model parameterization or analysis choices.
• Write high-quality, documented code for our internal codebase.
• Help translate your results into internal reports, publications, or patent disclosures.

What you'll need#

• Current enrollment in a doctoral program in materials science, computer science, statistics, applied math, machine learning, physics, or a related field.
• Strong foundations in machine learning, linear algebra, probability, and optimization.
• Experience training models on real datasets.
• Familiarity with representation learning or scientific machine learning.
• Proficiency in Python and modern ML tooling.
• Ability to work collaboratively across disciplines and translate research ideas into working code.
• Experience studying model convergence, learning dynamics, symmetries, or identifiability is a plus.

Location & details#

• Location: Los Altos, California.
• Term: Summer 2027.
• Work Modality: Hybrid.
• Commitment: Full-time.
• Compensation: This is a paid position with an expected pay range of $45 to $65 per hour. We provide medical, dental, and vision insurance along with paid time off.