Co-Op, Agentic Simulations for Materials Science

Lila Sciences • Cambridge, MA

9d

About The Position

Join Lila Sciences’ physical sciences team to help develop machine-learning- and agent-driven infrastructure that enables its scientific superintelligence to autonomously construct, execute, and interpret complex physics simulations and apply them to real-world problems in materials science and chemistry. Projects may focus on enabling AI agents to reason over and orchestrate simulations, developing machine-learning methods to accelerate atomistic simulations, or applying agentic simulations to materials discovery.

The role involves developing in-silico materials-discovery methods and workflows that connect physics-based simulations, generative models, and agentic AI systems. You will build pipelines in which AI agents autonomously design, launch, interpret, and refine simulations, and design machine-learning surrogate methods to accelerate simulations. You will collaborate with computational scientists, machine-learning experts, and platform engineers to integrate discovery pipelines into Lila’s broader scientific superintelligence ecosystem.

Lila Sciences is building Scientific Superintelligence to address major challenges. It combines advanced AI models with proprietary AI Science Factory instruments in an operating system for science designed to execute the scientific method autonomously across medicine, materials, and energy. The company describes its core values as truth, trust, curiosity, grit, and velocity, and encourages applications from candidates who may not meet every listed qualification.

Requirements

• Currently enrolled in an MS or PhD program in computer science, materials science, chemistry, chemical engineering, physics, or a related field; exceptional BS candidates with research experience may be considered.
• Proficiency in Python, deep-learning frameworks, and end-to-end workflow deployment.
• Evidence of applied machine-learning research in the physical sciences, including method development, model training and evaluation, and sound coding practices.
• Strong communication and presentation skills, with the ability to convey technical information clearly and thoroughly.
• Eagerness to work with highly skilled, dynamic teams in a fast-paced, entrepreneurial, and technical setting.

Nice To Haves

• Prior experience and publications in one or more of the following: machine-learning interatomic potential development, LLMs for materials science and chemistry, generative models for materials, or high-throughput computational materials discovery.
• Contributions to open-source simulation or machine-learning infrastructure and software.
• Familiarity with materials-science simulation codes and workflow orchestration frameworks.

Responsibilities

• Contribute to projects involving AI agents for simulations, machine-learning models for atomistic simulations, or in-silico materials discovery.
• Develop in-silico materials-discovery methods and workflows that connect physics-based simulations, generative models, and agentic AI systems.
• Build pipelines where AI agents can autonomously design, launch, interpret, and refine simulations.
• Design methods to accelerate simulations using machine-learning-based surrogate models.
• Collaborate with computational scientists, machine-learning experts, and platform engineers to integrate in-silico discovery pipelines into Lila’s scientific superintelligence ecosystem.

What This Job Offers

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