About the role#
The Physical Sciences AI team works where R&D meets machine learning. Lila conducts high-throughput experiments in electrochemistry, formulations, and materials. These experiments create datasets that require more than standard black-box models. In this role, you will develop and benchmark methods to extract interpretable governing equations from experimental data. These equations help explain physics and serve as building blocks for digital twins and closed-loop optimization. You will work with researchers and physical scientists to turn experimental data into scientific results.
What you'll do#
- Build end-to-end equation discovery pipelines, from preprocessing to validation.
- Benchmark symbolic regression methods on internal campaign data.
- Apply equation discovery to live electrochemistry, formulation, and materials datasets.
- Design evaluation harnesses to 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 clear baselines and success criteria.
- Document and present findings to PS AI and domain science teams.
What you'll need#
- Current pursuit of a Master's or PhD in ML, CS, applied math, physics, materials science, or chemical engineering.
- Strong Python skills and hands-on experience with PyTorch or JAX.
- Experience applying machine learning to real-world, messy scientific data.
- A solid foundation in linear algebra, calculus, and probability.
- Ability to read and implement methods from research papers.
- Skill in framing open-ended scientific questions as concrete ML tasks.
- Clear communication skills for working across research, engineering, and physical science teams.
- Bonus points for knowledge of symbolic or sparse regression (SINDy, PySR, PDE-FIND), LLM-guided symbolic regression, physics-informed ML (PINNs, neural ODEs), or digital twin workflows. Domain knowledge in electrochemistry, formulations, or materials science is also helpful.
Location & details#
- Locations: Cambridge, Massachusetts or San Francisco, California.
- Modality: On-site.
- Status: Full-time, paid internship.
- Term: Rolling.
About Lila Sciences
Lila Sciences operates as a scientific superintelligence platform and autonomous lab. The company focuses on life, chemistry, and materials science. It applies artificial intelligence to the scientific method to assist with research in human health and sustainability. Founded in 2023, the organization maintains its headquarters in Cambridge, Massachusetts. It currently employs 474 people.
How to get in at Lila Sciences
Applying early gives you a distinct advantage at Lila Sciences, as recruiters often review candidates before the applicant pool grows too large. Intern Insider sends an instant alert the moment a role matching your target is published, helping you stay at the front of the line. This timing matters when competition for technical roles is high. You can use this lead to prepare your materials before the position gains wider visibility. Reaching out to the right people often yields better results than submitting an application into a general queue. Intern Insider surfaces the recruiters behind the company's roles, which allows you to contact them directly for a referral or to ask specific questions about the work. A direct connection can improve your response rates and help you stand out from the pile.
