PhD Position in Machine Learning for Photocatalysis: The Digital Chemistry Laboratory at ETH Zurich is seeking a committed and motivated PhD candidate to develop machine learning methods for predicting the reactivity and selectivity of energy-transfer-catalyzed photocycloaddition reactions. This interdisciplinary project aims to advance the understanding of chemical reactivity through digital tools and collaboration with leading experts in the field.
Designation
PhD Candidate in Machine Learning for Photocatalysis
Research Area
- Digital Chemistry
- Machine Learning
- Photocatalysis
- Molecular Design
- Computational Chemistry
Location
ETH Zurich, Zurich, Switzerland
Eligibility/Qualification
- A Master’s degree in chemistry, chemical engineering, computational science, materials science, physics, or related fields (or expected graduation before the starting date).
- Proficiency in English.
- Self-motivated with the ability to work independently.
- An interdisciplinary mindset and a collaborative approach.
- Programming experience in languages such as Julia, Python, R, etc.
Desirable Experience (Not Mandatory)
- Hands-on experience in machine learning from projects or thesis.
- Experience in quantum-chemical simulations.
- Experience in organic synthesis from research projects or thesis.
Job Description
As a PhD candidate, you will:
- Develop machine learning methods for predicting reactivity and selectivity in photocycloaddition reactions.
- Identify descriptors for photochemical reactions to enhance model generalization.
- Collaborate closely with experimental partners in the Glorius group.
- Contribute to the teaching activities within the department.
How to Apply
Interested candidates should submit their applications through the online application portal of ETH Zurich. The application must include:
- A cover letter
- A curriculum vitae
- Copies of BSc and MSc educational records
Note:
Applications submitted via email or postal services will not be considered.
Last Date to Apply
All applications must be submitted by May 31.
