Computational Chemistry Co-op, Closed-Loop Ligand Design and Optimization

About the role#

The Synthetic Product Development team is looking for a graduate student to join a 6-month co-op program in 2027. You will work on building a closed-loop platform that combines computational tools and experimental testing to improve how we design and optimize chiral ligands. This role is a chance to apply computational chemistry and machine learning to real-world challenges in catalyst design and ligand discovery.

What you'll do#

• Partner with synthetic chemists to identify selectivity challenges, design training sets, and validate computational predictions.
• Run DFT transition-state calculations to determine geometries and energies for chiral ligands.
• Create machine learning surrogate models and use Bayesian optimization to identify optimal ligand candidates.
• Test your computational predictions in the lab to refine future design cycles.
• Build and document the computational pipeline to ensure the work is scalable and reproducible.

What you'll need#

• Enrollment in a Ph.D. program in synthetic organic chemistry or a related field with a focus on computational chemistry.
• Hands-on laboratory experience in synthetic organic chemistry or catalysis.
• Practical experience with quantum chemistry calculations, specifically DFT.
• A working knowledge of Python and relevant scientific libraries.
• A foundation in machine learning concepts like model training, validation, and regression.
• Ability to work in a team and communicate technical approaches clearly.

Location & details#

• Location: New Haven, Connecticut.
• Term: Winter or Summer 2027.
• Modality: On-site, full-time.
• Compensation: $48 per hour.
• Requirements: US work authorization is required. This position does not provide sponsorship.