Applied AI​/ML Engineer; Property Prediction Foundational Models

Applied AI/ML Engineer (Property Prediction Foundational Models)

Join CuspAI as an Applied AI/ML Engineer to build and apply multi‑modal foundation models that accelerate the discovery of world‑changing molecules. Your work will bridge frontier AI research and production‑grade scientific applications.

CuspAI is the frontier AI company on a mission to solve the breakthrough materials needed to power human progress. While nature took billions of years to perfect molecules, we harness AI to unlock trillion‑dollar materials breakthroughs in months, not millennia. Our founding team is world‑class researchers in AI, chemistry and engineering.

Due to the rapid scaling of our scientific intelligence and data curation capabilities, we are seeking an Applied AI/ML Engineer to build and apply multi‑modal foundation models to solve a broad range of materials discovery tasks.

We’re aiming to start interviewing for this role in mid‑January and would like to make an offer by mid‑February.

You will own the development and integration of property prediction models and apply them to existing and future project workflows. Over time you will evolve our multi‑modal foundation models to handle increasingly complex scientific modalities.

• Model Development & Application
  • Own the development, integration, and evaluation of property prediction models within customer workflows, ensuring reliable deployment and performance.
  • Adapt and fine‑tune our core foundation models for specific property prediction applications to meet high‑stakes scientific requirements.
  • Contribute to the ongoing development of multi‑modal foundation models for molecular systems, designing architectures that handle diverse input and output modalities.
  • Implement uncertainty quantification methods to support Bayesian optimization pipelines, helping scientists navigate the vast space of potential materials.
• Engineering Excellence
  • Build robust learned representations that generalize across various downstream tasks.
  • Apply strong software engineering best practices to ensure all systems are scalable, reliable, and maintainable.
  • Support the deployment and integration of production‑grade foundation models into our core platform.
• Scientific Collaboration & Integration
  • Partner closely with our internal chemists and materials scientists to integrate computational and experimental workflows into one seamless optimization loop.
  • Proactively learn the technical vocabulary of materials science and experimental chemistry to facilitate deep, meaningful interactions with domain experts.
  • Contribute to our mission by ensuring all system designs align with CuspAI’s commitment to sustainability and solving the world’s most pressing physical challenges.

• Strong software engineering skills and a proven track record of building complex systems in a production or industrial environment.
• Significant experience building, training, and evaluating relevant ML models such as Graph Neural Networks, Transformers, or Generative Models.
• Educational background (Master’s degree or PhD) in Computer Science, Machine Learning, or a related quantitative field.
• For candidates without a PhD, 4–5 years of industry experience in an ML or software engineering role is highly preferred.
• A deep interest in the connection between AI and materials science or chemistry, and a willingness to rapidly learn the scientific vocabulary of the discipline.

• Prior experience applying machine learning models specifically to problems in materials science, chemistry, or molecular informatics.
• Exposure to multi‑modal training and how to combine these modalities in a meaningful way.
• Experience implementing uncertainty quantification methods or Bayesian optimization pipelines.
• Experience adapting and fine‑tuning foundation models for specific scientific property prediction applications.

This role could be based in Amsterdam, Berlin, Cambridge or London, with the expectation of being in the office three days per week. Regular travel to other offices for collaboration and project oversight may…