Due to growth, we are seeking an Application Scientist (Semiconductor Modelling & Design) * to strengthen our team in London on artificial intelligence for inorganic crystals, and to play a crucial part in driving our research and development efforts forward.

• Note that you would be joining as a ‘Member of Technical Staff’, but the indicative job title above hopefully helps to explain the nature of this role.

Hiring timeline: We’re aiming to start interviewing for this role in January and would like to make an offer by mid-Feb.

Your Impact

Your models, simulations and pipelines will directly influence what our materials search engine proposes and what our partners and customers test.

Your workflows will feed directly into our discovery platform, where improvements in electronic structure predictions and transport property models propagate immediately from training runs to candidate shortlists, to customer demonstrations, to experimental validation.

By bridging quantum mechanics, machine learning, and semiconductor chemistry/physics, you'll compress materials discovery cycles from years to months and unlock design principles for next-generation electronic devices and energy technology solutions that would be impossible through traditional approaches alone.

What You Will Do

Your simulation campaigns will span electronic structure and transport properties, generating training data and validating generative model outputs. You’ll also need to build and adapt reproducible, versioned workflows with clean metrics as necessary.

Partnering closely with the ML team, your work will inform generative model development and identify opportunities for accelerated predictions of charge and thermal transport. You’ll also work alongside the Platform Engineering team to integrate workflows for scalable execution and reusability.

Collaborating with customer-facing teams, you’ll play a key role in producing technical briefs, benchmarks and slides for internal and external audiences. Your contributions to the design and implementation of customer projects will be critical to our success in this area. This will include establishing end user requirements, opportunities for ML and simulation, implementation and application of workflows using the CuspAI platform.

Semiconductor Modelling and Design

• Design and operate workflows for semiconductor materials (from electronic structure to charge and heat transport)
• Train and deploy machine learning force fields for accelerated sampling of relevant degrees of freedom
• Contribute to the development and testing of inverse design models for crystals, including for device-relevant applications with uncertainty quantification and active learning strategies, where applicable

Interdisciplinary Collaboration

• Platform Engineering: Productionise workflows and models for deployment at scale
• ML: Co-design model and data interfaces and evaluation harnesses; close the loop with active learning and uncertainty-aware retraining
• Materials and Application Science: Collaborate on method development, validation against experimental observables, and applications
• Partnerships: Engage with partners and customers on technical scoping and securing materials discovery opportunities in semiconductor applications

Must Have Skills and Qualifications:

You could be great for this if you’re a builder-scientist who pairs deep semiconductor chemistry and physics knowledge with production-grade software and ML skills and wants to apply reproducible tools across electronic materials discovery.

• Strong electronic structure background (density functional theory, e.g. using VASP, Quantum ESPRESSO or similar) with expertise in physical properties
• Hands-on experience with charge (electron/ion) or heat transport in crystalline materials
• Proficiency in Python for materials (e.g. pymatgen or ASE)
• Experience training or deploying machine learning force fields (e.g. MACE, NequIP, M3GNet) for materials simulations
• Workflow orchestration experience with Linux/HPC (data versioning, testing, CI/CD pipelines)
• Ability to translate computational predictions into actionable design principles for experimental validation

Bonus Points (But Not Critical):

• Knowledge of techniques for treating crystal disorder, including special quasi-random structures, cluster expansion, or configurational averaging
• Experience with multiscale modelling approaches linking atomistic simulations to device-scale properties
• Familiarity with active learning frameworks for materials screening (e.g. Bayesian optimisation, uncertainty-aware sampling)

Additional Considerations

This role will be based in our London office , with the expectation of being in the office three days per week . Additionally, there may be regular travel required to other locations for collaboration and project work.

What we offer

• A competitive salary plus equity package so you have a stake in the success of the company
• 28 days holiday
• Professional development budget for scientific conferences and technical training
• Opportunity to work at the forefront of AI-driven scientific discovery with world-class researchers
• Direct impact on advancing materials science through cutting-edge technology
• Collaborative environment bridging AI research, computational chemistry, and experimental science

Join us in shaping the future of materials with AI. Together, we can create groundbreaking solutions for a more sustainable world. CuspAI is an equal opportunities employer committed to building a diverse and inclusive workplace . We do not discriminate on the basis of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy or related condition (including breastfeeding), veteran status, or any other basis protected by applicable law.

We actively encourage applications from all backgrounds and value the unique perspectives and contributions that diversity brings to our team. Please let us know If you require any specific adjustments during or after the interview process. We will do everything we can within reason to accommodate.