Co-op: AI-Driven Computational Catalyst Design

AstraZeneca GmbH; New Haven (CT); On-site; USD 56,000 - 76,000; Full time

Job summary

AstraZeneca GmbH's Alexion Synthetic Product Development (SPD) team seeks a PhD student in synthetic organic chemistry with a passion for data‑driven catalyst design for a 6‑month co‑op in early 2027. You will help build a closed‑loop platform that combines computation and bench testing to accelerate chiral ligand development and optimization.

You will work with chemists to define training sets, perform DFT transition‑state calculations, build ML models, and run Bayesian optimization campaigns,

Qualifications

• PhD student in synthetic organic chemistry with computational focus.
• Experience with quantum chemistry-based calculations (DFT) and transition-state theory.
• Hands-on lab experience in synthesis, catalysis, or related areas.
• Familiarity with Python and ML concepts; ability to interpret data.
• Strong communication and collaboration skills.

Responsibilities

• Identify key selectivity challenges and co-design training sets.
• Perform DFT transition-state calculations for chiral ligands.
• Develop ML surrogate models and Bayesian optimization campaigns.
• Test predictions experimentally and refine design cycles.
• Document and maintain the closed-loop computational pipeline.
• Present updates and final results to the SPD team.

Skills

DFT calculations

Computational chemistry

Python

Machine learning basics

Synthetic organic chemistry

Stereochemistry

Communication

Team collaboration

Self-motivation

Education

PhD student in synthetic organic chemistry

Tools

DFT software

Job description

AstraZeneca GmbH's Alexion Synthetic Product Development (SPD) team seeks a PhD student in synthetic organic chemistry with a passion for data‑driven catalyst design for a 6‑month co‑op in early 2027. You will help build a closed‑loop platform that combines computation and bench testing to accelerate chiral ligand development and optimization.

You will work with chemists to define training sets, perform DFT transition‑state calculations, build ML models, and run Bayesian optimization campaigns,