Co-op: Computational Catalyst Designer (DFT/ML)

Biopharma Careers; New Haven (CT); On-site; USD 55,000 - 83,000; Full time

Job summary

Alexion's Synthetic Product Development (SPD) team is seeking a motivated Ph.D. candidate in synthetic organic chemistry for a 6-month co-op in early 2027.

The role integrates computation and experiment to accelerate chiral ligand development and optimization, spanning preclinical to commercial stages. You will work on building a closed-loop platform, performing DFT and transition-state calculations, and developing ML surrogates with Bayesian optimization, then validate predictions

Qualifications

• Currently enrolled in a Ph.D. program in synthetic organic chemistry or a related field with a focus on computational chemistry.
• Practical experience with quantum chemistry-based calculations (such as DFT calculations), including transition-state theory and energy calculation workflows.
• Hands-on laboratory experience in synthetic organic chemistry, catalysis, or a related area, including the ability to execute experiments safely and interpret experimental results.
• Understanding of organic stereochemistry and asymmetric catalysis concepts relevant to chiral ligand design.
• Understanding of Python (or other programming languages), including use of relevant scientific libraries.
• Foundational understanding of machine learning concepts: model training, validation, overfitting, and regression/classification frameworks.
• Strong written and verbal communication skills.
• Demonstrated ability to work collaboratively in a team environment and contribute to shared goals.
• A strong work ethic and high level of self-motivation with a strong desire to learn and contribute to shared project goals.
• Must be available during the full 6-month term and maintain general availability during standard business hours.
• US Work Authorization is required at time of application. This role does not provide OPT sponsorship or support. Candidates authorized to work under CPT may be considered, subject to verification of eligibility and applicable company requirements.
• Prior experience in cheminformatics or data-driven research projects.
• Prior experience with Bayesian optimization frameworks or active learning pipelines.
• Familiarity with molecular descriptor generation, molecular fingerprints, or structure-activity/selectivity relationship modeling.
• Experience with feature-attribution or model-interpretability methods applied to chemical or materials data.

Responsibilities

• Partnering with synthetic chemists to identify key selectivity challenges, co-design chemically reasonable training sets, and validate computational predictions against experimental outcomes.
• Performing DFT transition-state calculations to determine energies and geometries for a seed library of chiral ligands.
• Developing machine learning surrogate models that predict diastereomeric ratios from molecular descriptors and implementing Bayesian optimization campaigns to sequentially identify optimal ligand candidates balancing selectivity, reactivity, and synthetic feasibility.
• Testing computational predictions experimentally and using the resulting data to refine subsequent design cycles.
• Building, maintaining, and documenting the closed-loop computational pipeline (DFT -> ML -> BO -> Exp) to ensure reproducibility, scalability, and knowledge transfer to the broader SPD team.
• Communicating scientific challenges and the technical approaches through regular updates and a final presentation.

Skills

Python

Machine learning basics

Data-driven design

Collaboration

Communication

Education

Ph.D. candidate in synthetic organic chemistry

Tools

DFT software

ML frameworks

Job description

Alexion's Synthetic Product Development (SPD) team is seeking a motivated Ph.D. candidate in synthetic organic chemistry for a 6-month co-op in early 2027.

The role integrates computation and experiment to accelerate chiral ligand development and optimization, spanning preclinical to commercial stages. You will work on building a closed-loop platform, performing DFT and transition-state calculations, and developing ML surrogates with Bayesian optimization, then validate predictions