AI Scientist I/II, Representation Learning for Materials Science

Lila Sciences

Cambridge (MA)

On-site

USD 176,000 - 304,000

Full time

14 days+

Application generator

A complete application in a minute — tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Bonus potential

Generous early equity

Job summary

A pioneering technology company is seeking an AI Scientist I/II to join their Physical Science division in Cambridge, MA. The successful candidate will design and implement algorithms for representation learning in materials science, collaborating with experts in the field. This full-time role demands proficiency in Python and understanding of advanced learning methods. The expected salary ranges from $176,000 to $304,000 annually with bonus opportunities.

Qualifications

Proficiency in Python and end-to-end workflow deployment.
Understanding of self-supervised and unsupervised learning methods.
Knowledge of materials science principles.

Responsibilities

Design and implement representation learning architectures.
Develop self-supervised and unsupervised learning approaches.
Partner with scientists to deploy algorithms for materials design.

Skills

Python

Deep learning frameworks

Attention to detail

Communication skills

Independent thinking

Education

PhD in Materials Science or related field

Tools

Computational materials science methods

Job description

AI Scientist I/II, Representation Learning for Materials Science

Join our Physical Science division to create, deploy and transform state‑of‑the‑art approaches for representation learning for diverse data structures related to materials science. Partner with materials science experts and other teams to develop novel representations and algorithms that capture fundamental structure and relationships across multimodal data streams, enabling frontier materials discovery.

What You’ll Be Building

Physics‑Informed, Multi‑Modal Representation Learning Algorithms: Design and implement novel representation learning architectures for materials data spanning diverse applications and underlying data types.
Self‑Supervised & Unsupervised Learning Methods: Develop self‑supervised and unsupervised learning approaches to discover meaningful materials representations and learned embeddings originating from diverse data streams.
Real‑World Validation & Deployment: Partner with materials scientists, chemists, and software engineers to deploy algorithms and models for real‑world materials design cases accelerating discovery.
Cross‑Functional Partnership: Work closely with R&D leadership, product managers, and automation specialists to translate scientific questions into modeling strategies, learning methods, and deployment for materials discovery.

What You’ll Need To Succeed

Proficiency in Python, deep learning frameworks, and end‑to‑end workflow deployment for scalable learning algorithms.
Understanding of state‑of‑the‑art representation learning methods (self‑supervised, unsupervised) and physics‑informed inductive biases (geometric deep learning methods), and their application to scientific problems such as materials science, chemistry, or biology.
Elementary understanding of materials science, physics and chemistry and how relevant principles can be infused into architectures and learning algorithms.
Strong self‑starter and independent thinker with strong attention to detail.
Demonstrated industry experience or academic achievement.
Excellent communication and presentation skills, capable of conveying technical information clearly and thoroughly.
Eager to work with highly skilled and dynamic teams in a fast‑paced, entrepreneurial, and technical setting.

Bonus Points For

PhD in Materials Science, Computer Science, Physics, Chemistry, or related field with strong publication record in machine learning (NeurIPS, ICML, ICLR) and scientific venues (Nature, Science, Cell Press Matter, IOP).
Experience with computational materials science methods (DFT, Molecular Dynamics).
Understanding of experimental materials science techniques related to synthesis and characterization.
Experience creating representation learning algorithms for uncommon data structures.

About Lila

Lila Sciences is the world’s first scientific superintelligence platform and autonomous lab for life, chemistry, and materials science. We are pioneering a new age of boundless discovery by building the capabilities to apply AI to every aspect of the scientific method. We introduce scientific superintelligence to solve humankind’s greatest challenges, enabling scientists to bring forth solutions in human health, climate, and sustainability at a pace and scale never experienced before. Learn more about this mission at www.lila.ai.

Compensation

We expect the base salary for this role to fall between $176,000—$304,000 USD per year, along with bonus potential and generous early equity. The final offer will reflect your unique background, expertise, and impact.

We’re All In

Lila Sciences is committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or Veteran status.

A Note to Agencies

Lila Sciences does not accept unsolicited resumes from any source other than candidates. The submission of unsolicited resumes by recruitment or staffing agencies to Lila Sciences or its employees is strictly prohibited unless contacted directly by Lila Science’s internal Talent Acquisition team. Any resume submitted by an agency in the absence of a signed agreement will automatically become the property of Lila Sciences, and Lila Sciences will not owe any referral or other fees with respect thereto.

Seniority level