Retrosynthesis Researcher, Machine Learning

Schrödinger•New York, NY

10h•Hybrid

About The Position

Schrödinger seeks a Retrosynthesis Researcher in Machine Learning (ML) to join us in our mission to transform the discovery of therapeutics and materials. Schrödinger has pioneered a physics-based software platform that enables discovery of high-quality, novel molecules for drug development and materials applications more rapidly and at lower cost compared to traditional methods. The software platform is used by biopharmaceutical and industrial companies, academic institutions, and government laboratories around the world. Our multidisciplinary drug discovery team also leverages the software platform to advance collaborative programs and its own pipeline of novel therapeutics to address unmet medical needs. As a member of our Machine Learning team, you’ll work at the forefront of computational chemistry and AI, contributing to high-impact research with real-world applications in small molecule drug discovery and materials science.

Requirements

PhD in Chemistry, Computational Chemistry, Cheminformatics, or a related field
A solid publication record that demonstrates expertise in retrosynthesis algorithms and computational chemistry
An ML expert who has applied AI tools to chemical reaction prediction or retrosynthesis (e.g., reaction templates, template-free approaches) and understands organic synthesis and reaction mechanisms
An experienced user of cheminformatics tools (e.g., RDKit, Open Babel)
A proficient Python programmer who’s familiar with ML tools like Pytorch, Tensorflow, and JAX
An excellent problem-solver who’s comfortable working collaboratively in a multidisciplinary research environment

Nice To Haves

Familiarity with chemical reaction databases (e.g., Reaxys, USPTO, Pistachio)
Knowledge of computer-aided synthesis planning (CASP) tools and retrosynthetic analysis software (e.g., AiZynthFinder, ASKCOS, IBM RXN)
A background in graph-based learning, attention mechanisms, and transformer architectures applied to chemical data
Familiarity with reaction condition prediction and reaction yield optimization.
Experience with Schrödinger Suite and LiveDesign
Experience with de novo design and generative machine learning methods
Experience with cloud computing and/or high-performance computing (HPC) resources
Exposure to quantum chemistry (DFT) is a plus

Responsibilities

Develop and implement AI/ML models (e.g., graph neural networks, transformer-based models) for retrosynthetic pathway prediction
Apply deep learning techniques to predict reaction outcomes, optimize reaction conditions, and identify novel synthetic routes
Curate and manage reaction datasets from literature, patents, and proprietary sources to train and validate predictive models
Integrate retrosynthesis tools with cheminformatics platforms and molecular modeling software
Collaborate with synthetic chemists to experimentally validate predicted retrosynthetic routes and optimize laboratory workflows
Contribute to scholarly publications in high-impact journals and represent the research group in conferences and workshops