Co-Op, AI-Driven Equation Discovery

Lila Sciences • San Francisco, MA

9d

About The Position

The PS AI team works at the intersection of Physical Sciences R&D and AI/ML. Lila runs high-throughput experiments across electrochemistry, formulations, and advanced materials, producing datasets that call for interpretable methods beyond black-box models. In this Co-Op role, you will develop and benchmark methods to extract governing equations from experimental data. These equations can reveal underlying physics, support explainable predictions, and serve as mechanistic components for digital twins and closed-loop optimization. You will collaborate with PS AI researchers and physical scientists to help turn experimental data into scientific understanding at scale.

The role involves building end-to-end equation-discovery pipelines, benchmarking symbolic-regression methods on Lila campaign data, and applying those methods to electrochemistry, formulation, and materials datasets. You will develop evaluation harnesses, integrate discovered equations into surrogate and physics-informed models and experimental digital twins, translate open scientific questions into concrete machine-learning tasks, and document and present findings to research and domain-science teams.

Lila Sciences is building Scientific Superintelligence™ by combining advanced AI models with proprietary AI Science Factory™ instruments in an operating system designed to execute the scientific method autonomously. Its stated areas of impact include medicine, materials, and energy. The company describes its values as truth, trust, curiosity, grit, and velocity, and encourages applicants to apply even if they do not meet every listed qualification.

Requirements

• Pursuing a Master's or PhD in machine learning, computer science, applied mathematics, physics, materials science, or chemical engineering.
• Strong Python skills and hands-on experience with PyTorch, JAX, or a similar framework.
• Experience applying machine learning to messy, real-world scientific or experimental data.
• Solid grounding in linear algebra, calculus, and probability.
• Comfort reading and implementing methods from machine-learning research papers.
• Ability to frame open-ended scientific questions as concrete machine-learning tasks.
• Clear communication across research, engineering, and physical-science teams.

Nice To Haves

• Working knowledge of symbolic or sparse-regression methods such as SINDy, PySR, or PDE-FIND.
• Experience with LLM-guided or agentic symbolic regression, such as LLM-SR or SR-Scientist.
• Background in physics-informed machine learning, uncertainty quantification, or operator learning, including PINNs, neural ODEs, FNO, or DeepONet.
• Exposure to digital-twin or closed-loop workflows, including model calibration, active learning, or Bayesian optimization.
• Domain knowledge in electrochemistry, formulations, superconductors, or materials science.

Responsibilities

• Build end-to-end equation-discovery pipelines, from preprocessing through candidate generation and validation.
• Benchmark symbolic-regression methods, including SINDy, PDE-FIND, PySR, and LLM-guided search, on Lila campaign data.
• Apply equation-discovery methods to electrochemistry, formulation, and materials datasets.
• Design evaluation harnesses that measure recovery rate, generalization, noise robustness, and physical consistency.
• Embed discovered equations into surrogate models, physics-informed models, and experimental digital twins.
• Translate open scientific questions into concrete problems with datasets, baselines, and success criteria.
• Document and present findings across PS AI and domain-science teams.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern